Commit graph

3198 commits

Author SHA1 Message Date
sabaimran
4ce17acd00 Set greeting message to longer text in default view. Only show two agents in mobile 2024-08-03 12:14:58 +05:30
sabaimran
6c35ee4960 Revert height of the side panel on the home page 2024-08-03 11:59:07 +05:30
Debanjum Singh Solanky
e66adf60c5 Have the home and chat page take full height, reduce greeting top space 2024-08-03 11:54:12 +05:30
Debanjum Singh Solanky
cf8745ef78 Improve structure of chat footer on mobile to put agents above input 2024-08-03 11:31:57 +05:30
Debanjum Singh Solanky
529ffdb7e3 Make Title, Chat Footer Icons larger to ease click, tap on Mobile 2024-08-03 11:23:29 +05:30
Debanjum Singh Solanky
8d1c5226ec Remove unnecessary debug logs 2024-08-03 09:55:31 +05:30
sabaimran
f136214290 Improve the nav menu in the not logged in experience 2024-08-03 09:44:04 +05:30
Debanjum Singh Solanky
d8fe677933 Prevent overflow on Search page by search results 2024-08-03 07:07:35 +05:30
Debanjum Singh Solanky
f3765a20b9 Improve content alignment on automation page for small screens
- Left align email, location, timezone pills on small screens
- Indent user enabled automations to improve delineation between
  sections
2024-08-03 07:05:15 +05:30
Debanjum Singh Solanky
a6e1b2c7cb Style nav menu button and expand nav menu item click area to full-width
Style profile pircture button on nav menu
 - Use primary colored ring around subscribed user profile on nav menu
 - Use gray colored ring around non-subscribed user profile on nav menu
 - Use upper case initial as profile pic for user with no profile pic

- Click anywhere on nav menu item to trigger action
  Previously the actual clickable area was smaller than the width of
  the nav menu item
2024-08-03 05:43:24 +05:30
Debanjum Singh Solanky
eed9e401a2 Improve alignment of title bar elements 2024-08-03 04:11:58 +05:30
sabaimran
f188396395 Prompt to login when authenticated, click on suggestion card
- Improve styling for the side panel when not logged in
2024-08-03 01:42:32 +05:30
sabaimran
9c5ff1699a Use new nav menu alignment in the settings page 2024-08-03 01:42:32 +05:30
sabaimran
b1d3979ed9 Fix navmenu in settings, share/chat pages 2024-08-03 01:42:21 +05:30
sabaimran
5f8b76c8f2 Fix layout/styling of the factchecker app 2024-08-03 01:07:59 +05:30
sabaimran
1bb746aaed Adjust spacing when side panel is opened 2024-08-03 01:07:59 +05:30
sabaimran
07b3bdf181 Update nav menu styling to include everything in one header
- Move the nav menu into the chat history side panel component, so that they both show up on one line
- Update all pages to use it with the new formatting
- in mobile, present the sidebar button, home button, and profile button evenly centered in the middle
2024-08-03 01:07:55 +05:30
Debanjum Singh Solanky
e62888659f Only show greeting once userConfig is fetched from server
- Pass userConfig from Home as prop to chatBodyData component with
  loading state
- Pass loading state of userConfig to allow components to handle
  rendering dependent elements once it is loaded
2024-08-02 20:25:09 +05:30
Debanjum Singh Solanky
0adee07d40 Update home page greetings to use user name, when available 2024-08-02 20:25:09 +05:30
sabaimran
5a8ea884a9
Use new HTTP stream format within the new UX
Use updated format for HTTP streamed responses from the Khoj server in the new chat UX
Remove references to the websocket connected field, as websocket use has been deprecated
2024-08-02 02:35:10 -07:00
Debanjum Singh Solanky
02b46a1784 Render references after chat response is streamed for smoother render
Otherwise the Khoj's chat response is filling up in between the
streamed message and already rendered references section at the bottom
of the message

Define OnlineContext type to simplify typing online context param
across other interfaces and functions
2024-08-02 14:11:34 +05:30
Debanjum Singh Solanky
a733e5c1d4 Remove unused handleCompiledReferences chat functions 2024-08-02 13:18:55 +05:30
Debanjum Singh Solanky
7858aff2e2 Trigger welcomeConsole only once on chat, shared chat page load 2024-08-02 13:18:01 +05:30
Debanjum Singh Solanky
cab0957fd3 Just show Khoj logo on title bar on small screens
Continue to show logo + text on larger screens
2024-08-02 13:18:01 +05:30
Debanjum Singh Solanky
3f607b3978 Add icons, improve description of home, chat & search page metadata 2024-08-02 13:18:01 +05:30
Debanjum Singh Solanky
4f783b911c Update DOMPurify imports correctly to resolve compilation warnings 2024-08-02 13:18:01 +05:30
sabaimran
4492017b96 Move processmessagechunk file into a common chat function 2024-08-02 12:31:43 +05:30
sabaimran
13dee7d89e Remove status update for understanding query 2024-08-01 19:22:21 +05:30
sabaimran
1b2cad2a2c Use af in the default state and configure the phone number input styling 2024-08-01 17:04:57 +05:30
sabaimran
723b37955a Disable input for phone number only if its pending verification 2024-08-01 16:45:38 +05:30
sabaimran
84dd1b57fe Use an intl phone input number field and fix the whole verification flow
- There were some state mismatches in configuring a whatsapp number. This commit fixes those issues and uses an external library for phone number validation
2024-08-01 16:44:17 +05:30
sabaimran
ed16914ac3 Remove deprecated fields and fix erroneous export in settings page 2024-08-01 14:45:54 +05:30
sabaimran
7941f4d54d Remove references to deprecated setupwebsocket function 2024-08-01 14:43:17 +05:30
sabaimran
db93ac5d4b Merge branch 'features/big-upgrade-chat-ux' of github.com:khoj-ai/khoj into features/use-new-sse-in-new-chat-ux 2024-08-01 14:41:50 +05:30
sabaimran
fd0e0405af Fix logic for setting and sending the initial chat message from the home page
- Load agents only once when the page loads, rather than triggering constant re-renders
2024-08-01 13:53:16 +05:30
sabaimran
9a43622cef Remove usages of the websocketconnected variable 2024-08-01 13:14:23 +05:30
sabaimran
bfeb64b48f Migrate the shared chat page to also use the new SSE streaming format 2024-08-01 13:14:09 +05:30
sabaimran
833553c3a3 Move conversation commands selection earlier to include in telemetry collected 2024-08-01 12:52:41 +05:30
sabaimran
dbbcf2564f Remove the usage of emojis in the incremental status updates 2024-08-01 12:52:05 +05:30
sabaimran
cd85a51980 Ingest new format for server sent events within the HTTP streamed response
- Note that the SSR for next doesn't support rendering on the client-side, so it'll only update it one big chunk
- Fix unique key error in the chatmessage history for incoming messages
- Remove websocket value usage in the chat history side panel
- Remove other websocket code from the chat page
2024-08-01 12:50:43 +05:30
Debanjum Singh Solanky
32ce564b7c Remove unused Files Connect button and setup Github content card 2024-07-30 18:55:14 +05:30
Debanjum Singh Solanky
ecb873c488 Only allow search model to be updated without being subscribed
Do not make fetch request to server if user is not subscribed
2024-07-30 18:50:57 +05:30
Debanjum Singh Solanky
f58cff5bcc Increase rate limit in the api/content vs deprecated indexer API 2024-07-30 16:09:26 +05:30
Debanjum Singh Solanky
f0bb6883f8 Improve Delete experience on Files Card in Settings Page
Improve placeholder text for notion API key and Whatsapp
number (mention country code required)
2024-07-30 15:25:14 +05:30
sabaimran
b1eb564706 remove the optional pydantic typing from the files param 2024-07-30 15:25:14 +05:30
sabaimran
4a7efdc552 Use patch in place of put in the indexer API call, ensure that files are not being required in the indexer path 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
ffbf57292c Create synced files management modal on the settings page
Use a Command Dialog to allow easier filtering of files to view
without having to leave the settings page
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
ccc46a09b5 Add new API to batch delete a list of files by filename
- Rearrange DELETE content API definitions order to go from more
  specific to more general
- Create batched file deletion DB adapter
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
9d86cb57ac Build UX to Connect and Manage Notion Integration via Settings Page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
7ee179ee1f Return user's Notion token in API call for detailed user settings 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
00a908ae12 Move subscription card to Profile settings section. Remove Billing section
- Why
  Profile section and billing section looked too empty (1 card each).
  Combining them makes the setting page look more complete. Shows
  subscription options early on
- Details
  - Made Futurist text orange
  - Made Unsubscribe a down button instead of cloud slash
  - Updated toast title to subscription
  - Improve Futurist trial title and description
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
058c902dc7 Delete unused npm package-lock.json as Web app uses yarn.lock instead 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
b8c9b3ffa3 Reduce padding height of input area on new home page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
8a447107dd Set user name on clicking Save button on settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
44e0b20202 Align Content, Client & Billing settings sections with new designs 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
51e83bcc26 Improve responsive behavior of settings cards 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
efcad4996d Add phone number verification for Whatsapp to new settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
48548684c0 Add card to connect Whatsapp to Khoj on settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
8ec90f194f Add title icons for each content section card on settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
60cdf61737 Create billing section for managing subscription on settings page
- Replicate behavior on current settings.html page
- Improve text for each subscription state to make it more informative, fun
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
2e165a0e0a Create client API keys section on settings page
- Add table shadcn component to use in API keys settings section
- In dev mode, route requests to auth to khoj server at localhost:42110
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
00fa4fa0fa Save model on selecting model in dropdown. No extra save action reqd
- Remove now unnecessary button to Save in Card with dropdown
- Use toast to show success, failure (not working)
- Rename language to search, Move it to features section. Add icon to
  the card
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
13292fc4ca Add icons to card headings 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
a5a06da3fc Use Dropdown component for model options. Make cards more responsive
- Ensure model name doesn't stretch or shrink dropdown width from
  parent card width
- Ensure buttons flex wrap on smaller displays
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
ade2f6f5d1 Rename selected voice model in get config API response for consistency
- Update references in new and old web client settings
- Arrange new client settings props and add header comments similar to
- config response for code readability
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
b3253562a5 Dynamically set Content cards buttons based on already setup or not 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
7e8e80f29e Create config page using tailwind, shadcn components, styling
- Include side pane but with only the account info in it
- Replicate styling of the old config page
2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
88007d7552 Get user config in the new web client from the new user config APIs 2024-07-30 15:25:14 +05:30
sabaimran
a6339bb973 Add mroe card suggestions and simplify color selection for suggestion cards 2024-07-29 19:11:39 +05:30
sabaimran
551630f0f1 Code clean-up and some fit and finish
- Add a lot more suggestions cards, improve mobile rendering of suggestion cards, improve alignment of chat input, shift message when starts recording voice, remove dead code
2024-07-28 15:19:36 +05:30
sabaimran
1a1d9c7257 Merge branch 'master' of github.com:khoj-ai/khoj into features/big-upgrade-chat-ux 2024-07-27 14:18:05 +05:30
Raghav Tirumale
1685c60e3c
Nav Menu Upgrades and Minor UX Improvements (#869)
* Converted navigation menu into a dropdown menu
* Moved collapsed side panel menu icons into top row
* Auto refresh when conversation is deleted to update side panel and route back to main page if deletion is on current conversation
* Highlight the current conversation in the side panel
* Dynamic homepage messages with current day and time of day.
* `colorutils` upgraded to have more expansive tailwind color options and dynamic class name generation.
* Converted create agent button alert into shadcn `ToolTip`
* Colored lines and icons for agents in chat window
* Cleaned up border styling in dark mode
* fixed three dot menu in side panel to be more easier to click
* Add the KhojLogo import in the nav menu and use a default user profile icon when not authenticated
* Get rid of custom --box-shadow CSS variable
* Pass the agent metadat through the chat body data in order to style the send button
* Add login to the unauthenticated login view, redirecto to home if conversation history not loaded
* Set a max height for the input text area
* Simplify tailwind class names

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-07-27 14:12:00 +05:30
Debanjum
8503d7a07b
Split Configure API into Content, Model API paths (#857)
## Major: Breaking Changes
- Move API endpoints under /configure/<type>/model to /api/model/<type>
- Move API endpoints under /api/configure/content/ to /api/content/
- Accept file deletion requests by clients during sync
- Split /api/v1/index/update into /api/content PUT, PATCH API endpoints

## Minor: Create New API Endpoint
- Create API endpoints to get user content configurations

Related: #852
2024-07-26 23:48:41 -07:00
Debanjum Singh Solanky
a47a54f207 Pass user name to document and online search actors prompts
This should improve the quality of personal information extraction
from document and online sources. The user name is only used when it
is set
2024-07-26 23:53:17 +05:30
sabaimran
e86143dbb0
Merge pull request #867 from khoj-ai/features/search-page-v2
Update the search page
2024-07-26 08:08:04 -07:00
sabaimran
eb5af38f33 Release Khoj version 1.17.0 2024-07-26 20:14:45 +05:30
Raghav Tirumale
5dcac18ba5
New Agents Page User Interface (#866)
Changes for new agents page
- Modernized agent cards
- Responsive design to support mobile users
- Button for users to create their own agents (coming soon)
- Optimized to use tailwind and icon utils
- Side panel added for quick access to conversations
2024-07-26 20:12:31 +05:30
Debanjum Singh Solanky
3daef910c0 Remove stale comment from api content 2024-07-26 20:05:35 +05:30
sabaimran
377f7668c5
Merge pull request #858 from khoj-ai/use-sse-instead-of-websocket
Use Single HTTP API for Robust, Generalizable Chat Streaming
2024-07-26 07:11:54 -07:00
sabaimran
6607e666dc Increase rate limit for data upload packet size in indexer.py 2024-07-26 19:35:32 +05:30
Debanjum Singh Solanky
778c571288 Use enum to track chat stream event types in chat api router 2024-07-26 00:19:43 +05:30
sabaimran
7482797605 Add some better default states for no files found, prompt to search. Add link to search in the file search compnoent in side panel 2024-07-25 13:00:28 +05:30
sabaimran
662dffea3b Press enter to search 2024-07-24 19:28:38 +05:30
sabaimran
19cd607c96 Style the see content button correctly 2024-07-24 18:28:23 +05:30
sabaimran
75a370cc06 Implement focus mode to click into full text of the note 2024-07-24 18:00:33 +05:30
sabaimran
5adbfe14ab Add a search page that just renders truncated results when you click search 2024-07-24 17:43:19 +05:30
sabaimran
52db15706d Remove unused styling 2024-07-24 17:42:36 +05:30
sabaimran
cfe7a1068e Update the navmenu title if prop is updated and undefined 2024-07-24 17:41:31 +05:30
Debanjum Singh Solanky
ebe92ef16d Do not send references twice in streamed image response
Remove unused image content to reduce response payload size.
References are collated, sent separately
2024-07-24 17:18:14 +05:30
Debanjum Singh Solanky
37b8fc5577 Extract events even when http chunk contains partial or mutiple events
Previous logic was more brittle to break with simple unbalanced
'{' or '}' string present in the event data. This method of trying to
identify valid json obj was fairly brittle. It only allowed json
objects or processed event as raw strings.

Now we buffer chunk until we see our unicode magic delimiter and only
then process it.

This is much less likely to break based on event data and the
delimiter is more tunable if we want to reduce rendering breakage
likelihood further
2024-07-24 17:17:39 +05:30
sabaimran
4d30e5b158 Fix indexing error for notion, expecting image and docx in dict 2024-07-24 16:58:31 +05:30
sabaimran
694bedc25b
Add support for text to speech and speech to text (#863)
- Add support for text to speech, speech to text. Add loading and responsive indicators to reflect state.
- When streaming for speech to text, show incremental transcription in the message input field
- When streaming text to speech, and a pause button in the chat message to allow user to stop playback
2024-07-24 14:36:40 +05:30
Raghav Tirumale
3e4325edab
Upgrade: New Home Screen for Khoj (#860)
* V1 of the new automations page
Implemented:
- Shareable
- Editable
- Suggested Cards
- Create new cards
- added side panel new conversation button
- Implement mobile-friendly view for homepage
- Fix issue of new conversations being created when selected agent is changed
- Improve center of the homepage experience
- Fix showing agent during first chat experience
- dark mode gradient updates

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-07-24 13:16:19 +05:30
Debanjum Singh Solanky
70201e8db8 Log total, ttft chat response time on start, end llm_response events
- Deduplicate code to collect chat telemetry by relying on
  end_llm_response event
- Log time to first token and total chat response time for latency
  analysis of Khoj as an agent. Not just the latency of the LLM
- Remove duplicate timer in the image generation path
2024-07-23 23:21:12 +05:30
Debanjum Singh Solanky
b36a7833a6 Remove the old mechanism of streaming compiled references
Do not need response generator to stuff compiled references in chat
stream using "### compiled references:" separator.

References are now sent to clients as structured json while streaming
2024-07-23 19:53:51 +05:30
Debanjum Singh Solanky
eb4e12d3c5 s/online_context/onlineContext chat API response field for consistency
This will align the name of the online context field returned by
current chat message and chat history
2024-07-23 19:50:43 +05:30
Debanjum
498fe2458c
Support Gemma 2 Model Family for Offline Chat (#855)
## Overview
- Gemma 2 is a new open model family by Google. They've released a 9B, 29B param model. A 2B model is also expected.
- It performs really well on the Chatbot arena and shows good performance when testing within Khoj as well.
- Llama.cpp support for Gemma 2 architecture seems to have stabilized
- If Gemma 2 performs well in further testing, it can be made the default offline chat model for Khoj
  - Once the 2B param model is released, the model size to download can be automatically chosen based on (V)RAM available

## Major
- Support Gemma 2 for Offline Chat
- Improve and fix chat model prompts for better, consistent context

## Minor
- Fix and improve offline chat actor, director tests
- Improve offline chat truncation to consider chat message delimiter tokens
2024-07-23 06:57:02 -07:00
Debanjum Singh Solanky
0277d16daf Share desktop chat streaming utility funcs across chat, shortcut views
Null check menu, menuContainer to avoid errors on Khoj mini
2024-07-23 19:16:33 +05:30
Debanjum Singh Solanky
e439a6ddac Use async/await in web client chat stream instead of promises
Align streaming logic across web, desktop and obsidian clients
2024-07-23 18:17:47 +05:30
Debanjum Singh Solanky
fafc467173 Put loading spinner at bottom of chat message in web client 2024-07-23 18:17:47 +05:30
Debanjum Singh Solanky
fc33162ec6 Use new chat streaming API to show Khoj train of thought in Desktop app
Show loading spinner at end of current message
2024-07-23 18:17:47 +05:30
Debanjum Singh Solanky
c5ad172616 Keep loading animation at message end & reduce lists padding in Obsidian
Previously loading animation would be at top of message. Moving it to
bottom is more intuitve and easier to track.

Remove white-space: pre from list elements. It was adding too much y
axis padding to chat messages (and train of thought)
2024-07-23 17:56:03 +05:30
Debanjum Singh Solanky
54b4203683 Update chat API client tests to mix testing of batch and streaming mode 2024-07-23 17:56:03 +05:30
Debanjum Singh Solanky
3f5f418d0e Use new chat streaming API to show Khoj train of thought in Obsidian client 2024-07-23 17:56:03 +05:30
Debanjum Singh Solanky
8303b09129 Convert snake case to camel case in chat view of obsidian plugin 2024-07-23 15:29:12 +05:30
Debanjum Singh Solanky
b224d7ffad Simplify get_conversation_by_user DB adapter code 2024-07-23 14:51:11 +05:30
Debanjum Singh Solanky
daec439d52 Replace old chat router with new chat router with advanced streaming
- Details
  Only return notes refs, online refs, inferred queries and generated
  response in non-streaming mode. Do not return train of throught and
  other status messages

  Incorporate missing logic from old chat API router into new one.

- Motivation
  So we can halve chat API code by getting rid of the duplicate logic
  for the websocket router

  The deduplicated code:
  - Avoids inadvertant logic drift between the 2 routers
  - Improves dev velocity
2024-07-23 14:51:11 +05:30
Debanjum Singh Solanky
2d4b284218 Simplify streaming chat function in web client 2024-07-23 14:38:55 +05:30
Debanjum Singh Solanky
6b9550238f Simplify advanced streaming chat API, align params with normal chat API 2024-07-22 22:51:24 +05:30
Debanjum Singh Solanky
b8d3e3669a Stream Status Messages via Streaming Response from server to web client
- Overview
Use simpler HTTP Streaming Response to send status messages, alongside
response and references from server to clients via API.

Update web client to use the streamed response to show train of thought,
stream response and render references.

- Motivation
This should allow other Khoj clients to pass auth headers and recieve
Khoj's train of thought messages from server over simple HTTP
streaming API.

It'll also eventually deduplicate chat logic across /websocket and
/chat API endpoints and help maintainability and dev velocity

- Details
  - Pass references as a separate streaming message type for simpler
    parsing. Remove passing "### compiled references" altogether once
    the original /api/chat API is deprecated/merged with the new one
    and clients have been updated to consume the references using this
    new mechanism
  - Save message to conversation even if client disconnects. This is
    done by not breaking out of the async iterator that is sending the
    llm response. As the save conversation is called at the end of the
    iteration
  - Handle parsing chunked json responses as a valid json on client.
    This requires additional logic on client side but makes the client
    more robust to server chunking json response such that each chunk
    isn't itself necessarily a valid json.
2024-07-22 15:41:21 +05:30
Debanjum Singh Solanky
91fe41106e Convert Websocket into Server Side Event (SSE) API endpoint
- Convert functions in SSE API path into async generators using yields
- Validate image generation, online, notes lookup and general paths of
  chat request are handled fine by the web client and server API
2024-07-21 14:20:22 +05:30
sabaimran
9cf52bb7e4
Update automations UX for more consistency (#856)
* Update the automations UI to be a more suitable color distribution based on new designs

* Use accented colors for the metadata, update dark mode colors

* Update form to use icons as well and render more pretty inline form labels
2024-07-21 12:22:23 +05:30
sabaimran
7426a4f819 Prefetch related agent when retrieving the conversation for performance improvements 2024-07-19 14:43:30 +05:30
Debanjum Singh Solanky
07f36fa95a Update new web interface with update calls to /content, /model APIs 2024-07-19 12:23:22 +05:30
Debanjum Singh Solanky
f03525f431 Add back /api/configure as /api/settings API endpoint
It had been removed during the /api/configure/content to /api/content
API migration before
2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
3832ef0236 Move API endpoints under /api/configure/phone/ to /api/phone/
Pull out /api/configure/phone API endpoints into /api/phone for
more concise and sufficiently explanatory API path

Refactor Flow
1. Rename /api/configure/phone -> /api/phone
2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
1197266912 Move API endpoints under /configure/<type>/model to /api/model/<type>
Now the API to configure all the AI models is under /api/models.
This provides better organization and API hierarchy. The /configure
url segment was redundant.

- Rename POST /api/phone to PATCH /api/phone
- Rename GET /api/configure to GET /api/settings

Refactor Flow
1. Move out POST /user/name to main api.py
2. Rename /api/configure/<type>/model -> /api/model/<type>
3. Rename @api_configure to @api_mode
4. Rename file api_config.py to api_model.py
2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
469a1cb6a2 Move API endpoints under /api/configure/content/ to /api/content/
Pull out /api/configure/content API endpoints into /api/content to
allow for more logical organization of API path hierarchy

This should make the url more succinct and API request intent more
understandable by using existing HTTP method semantics along with the
path.

The /configure URL path segment was either
- redundant (e.g POST /configure/notion) or
- incorrect (e.g GET /configure/files)

Some example of naming improvements:
- GET /configure/types -> GET /content/types
- GET /configure/files -> GET /content/files
- DELETE /configure/files -> DELETE /content/files

This should also align, merge better the the content indexing API
triggered via PUT, PATCH /content

Refactor Flow
1. Rename /api/configure/types -> /api/content/types
2. Rename /api/configure -> /api
3. Move /api/content to api_content from under api_config
2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
bba4e0b529 Accept file deletion requests by clients during sync
- Remove unused full_corpus boolean. The full_corpus=False code path
  wasn't being used (accept for in a test)
- The full_corpus=True code path used was ignoring file deletion
  requests sent by clients during sync. Unclear why this was done
- Added unit test to prevent regression and show file deletion by
  clients during sync not ignored now
2024-07-19 04:53:01 +05:30
Debanjum Singh Solanky
5923b6d89e Split /api/v1/index/update into /api/content PUT, PATCH API endpoints
- This utilizes PUT, PATCH HTTP method semantics to remove need for
  the "regenerate" query param and "/update" url suffix
- This should make the url more succinct and API request intent more
  understandable by using existing HTTP method semantics
2024-07-19 01:45:53 +05:30
Debanjum Singh Solanky
b0ee78586c Improve offline chat truncation to consider message separator tokens 2024-07-18 03:43:09 +05:30
Debanjum Singh Solanky
6f46e6afc6 Improve and fix chat model prompts for better, consistent context
- Add day of week to system prompt of openai, anthropic, offline chat models
- Pass more context to offline chat system prompt to
  - ask follow-up questions
  - know where to find information about khoj (itself)
- Fix output mode selection prompt. Log error if model does not select
  valid option from list of valid output modes provided
- Use consistent names for question, answers passed to
  extract_questions_offline prompt

- Log which model extracts question, what the offline chat model sees
  as context. Similar to debug log shown for openai models
2024-07-18 03:43:09 +05:30
Debanjum Singh Solanky
53eabe0c06 Support Gemma 2 for Offline Chat
- Pass system message as the first user chat message as Gemma 2
  doesn't support system messages
- Use gemma-2 chat format
- Pass chat model name to generic, extract questions chat actors
  Used to figure out chat template to use for model
  For generic chat actor argument was anyway available but not being
  passed, which is confusing
2024-07-18 03:09:38 +05:30
Debanjum Singh Solanky
65dade4838 Create API endpoints to get user content configurations
This is to be used by the new Next.js web client
2024-07-17 13:41:14 +05:30
Debanjum Singh Solanky
a1c362a4f7 Expose web, desktop settings page under /settings, not /configure
- Update references to the settings page to use new url across docs
  and code
- Rename desktop and web settings page to settigns.html instead of
  config[ure].html
2024-07-17 13:17:29 +05:30
Debanjum Singh Solanky
b015b0e83d Arrange config API detailed response fields to improve readability
There are a lot of fields being returned. Group returned fields and
add comment header to each Group for readability
2024-07-17 13:17:28 +05:30
Debanjum Singh Solanky
71ebf31a54 Make config API detailed response fields more intuitive, consistent
- Use name, id for every [search|chat|voice|pain]_model_option
- Rename current_model_state field to more intuitive enabled_content_source
- Update references to the update fields in config.html
2024-07-17 12:41:01 +05:30
Debanjum Singh Solanky
583fa3c188 Migrate the pypi package to khoj project name. Update references
- Deprecate khoj-assistant pypi package. Use more accurate and
  succinct pypi project name, khoj
- Update references to sye khoj pypi package in docs and code instead
  of the legacy khoj-assistant pypi package
- Update pypi workflow to publish to both khoj, khoj-assistant for now
- Update stale python 3.9 support mentioned in our pyproject. Can't
  support python 3.9 as depend on latest django which support >=3.10
2024-07-17 10:41:16 +05:30
Debanjum Singh Solanky
7316e6b9d3 Pass isMobileWidth prop to SidePanel via chat share interface 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
4759c4ac96 Turn prettier off instead of throwing error for now
Until web interface code is reformatted with prettier
2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
466ef3f8f1 Do no explicitly add line-clamp plugin as it's in Tailwind by default 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
59000a47cb Move Desktop config page to /configure from /config url path
Update references to point to page at /configure instead of /config
2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
a5c16ad600 Move Web client config page to /configure from /config url path
Update docs, clients and error messages to point to /configure
instead of /config
2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
de15a7a3fc Rename API path /api/config to /api/configure
- Update clients calling /api/config to call /api/configure instead
2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
dd31936746 Make config api endpoint urls consistent
- Consistently use /content/ for data. Remove content-source from path
- Remove unnecessary /data/ prefix for API endpoints under /config
2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
e8176b41ef Reuse get config data logic across config pages on web client
- Put logic to get config data, detailed or basic into router helpers module
- Use the get config func across the config pages on web clients

- Put configure content and get_notion_auth_url funcs in router helper
  module to avoid circular import
2024-07-16 16:13:27 +05:30
sabaimran
1a5405e24c Fix interpretation of day of week in automation form 2024-07-16 10:12:30 +05:30
sabaimran
c837f3779e
Update the agents page with new UX (#850)
- Use icons/colors for setting the styling of agents
- Update automations page to use the shadcn cards: https://github.com/shadcn-ui/ui
2024-07-16 10:10:55 +05:30
sabaimran
1c6ed9bc6d
Migrate the existing automations page to use React (#849)
Migrates the Automations page to React, mostly keeping the overall design consistent with organization. Use component library, with some changes in color. Add easier management with straightforward form and editing experience.
Use system preference for determining dark mode if not explicitly set.
2024-07-15 21:42:33 +05:30
Debanjum Singh Solanky
6c630bc6c3 Constrain chat messages to stay in view port across screen sizes
- Constrain chat messages max width to view port across screen sizes
- Wrap references on smaller screens, use tailwind, not js to apply styling
2024-07-15 21:00:50 +05:30
sabaimran
9a5bf4c701 Fix rendering of teaser reference panel in mobile width 2024-07-15 19:40:55 +05:30
sabaimran
2e9275c0f3 Remove side panel padding in desktop view. Fix width in mobile view 2024-07-15 19:33:12 +05:30
Debanjum Singh Solanky
ba0ba6b59f Merge branch 'features/big-upgrade-chat-ux' of github.com:khoj-ai/khoj into document-styling-on-chat-ux 2024-07-15 10:42:56 +05:30
Debanjum
23f61d49e0
Support syncing, searching images from Obsidian plugin (#847)
- Sync images from Obsidian vault with Khoj server now that Khoj can OCR images
- Support rendering images returned by Khoj search modal
2024-07-14 20:41:39 -07:00
Debanjum Singh Solanky
6f8f846086 Standardize code format for web interface with prettier
Use husky, lint-staged to run prettier pre-commit
2024-07-15 00:34:54 +05:30
sabaimran
06dce4729b
Make most major changes for an updated chat UI (#843)
- Updated references panel
- Use subtle coloring for chat cards
- Chat streaming with train of thought
- Side panel with limited sessions, expandable
- Manage conversation file filters easily from the side panel
- Updated nav menu, easily go to agents/automations/profile
- Upload data from the chat UI (on click attachment icon)
- Slash command pop-up menu, scrollable and selectable
- Dark mode-enabled
- Mostly mobile friendly
2024-07-14 23:18:06 +05:30
Debanjum Singh Solanky
6dd90931e8 Fix closing side panel on mobile when click open a chat session 2024-07-14 22:54:49 +05:30
Debanjum Singh Solanky
47b754c07b Only open side panel as drawer in mobile view 2024-07-14 14:08:41 +05:30
Debanjum Singh Solanky
b47f30ad77 Make Khoj icon appropriately sized and side panel arrow bold 2024-07-14 14:06:36 +05:30
Debanjum Singh Solanky
e6b21144e2 Conversations list should resize to take max space on side panel 2024-07-14 13:49:36 +05:30
Debanjum Singh Solanky
c2bf405489 Make loading message, styling configurable. Do not show agent when no data
- Pass Loading message, class name via props to both inline and normal
  loading spinners
- Pass loading conversation message to loading spinner when chat
  history is being fetched
2024-07-14 13:00:36 +05:30
Debanjum Singh Solanky
63719747cb Show agent profile card with description when hover on agent in chat view
- Create profile card componennt. Use it for agent profile card
- Pass agent persona from khoj server via API
- Put link to agent profile page in the hover card to make it 2 clicks
  away. Othewise inadvertent clicks on agent in chat view lead away to
  agent page
- Use tailwind line-clamp extension to clamp card to first two lines
2024-07-14 12:20:11 +05:30
Debanjum Singh Solanky
dbbd4b9777 Show action bar on last chat message without hover 2024-07-14 10:32:31 +05:30
Debanjum Singh Solanky
a0f38e079f Improve Train of Thought icons spacing and loading circle 2024-07-14 09:35:15 +05:30
Debanjum Singh Solanky
e9567741eb Improve mobile friendly styling of chat session side panel 2024-07-14 00:57:08 +05:30
Debanjum Singh Solanky
b26a6e25d1 Show chat message action buttons without hover on mobile interfaces
This is because hover maybe hard to do on mobile devices
2024-07-14 00:54:23 +05:30
Debanjum Singh Solanky
f69f9e3523 Close chat sessions side panel on click open a chat session 2024-07-14 00:53:16 +05:30
Debanjum Singh Solanky
d51011314f Improve styling of chat input, references UI across screen sizes
Use tailwind screen breakpoints shorthand instead of js to apply
different styling for different screen sizes
2024-07-13 20:45:34 +05:30
Debanjum Singh Solanky
2668e42e7f Center cursor in chat input. See upto 2 lines for multi-line context
- Reuse class name when get slash command icons
- Previous chat input styling didn't have the cursor centered in the
  chat input text area. But it did allow seeing multi line chat inputs
  for context
2024-07-13 02:51:29 +05:30
Debanjum Singh Solanky
aeaebfb515 Show chat message timestamp on hover in chat view 2024-07-13 02:51:19 +05:30
Debanjum Singh Solanky
e00c6b486e Add hover text descriptions of action buttons on chat message in web view 2024-07-12 15:40:51 +05:30
Debanjum Singh Solanky
5fccccfdff Do not render references with broken links in chat view 2024-07-12 15:14:11 +05:30
Debanjum Singh Solanky
b98a0cfe1b Render inline png, webp images generated by Khoj in chat view
Add spacing between chat message paragraphs
2024-07-12 15:13:19 +05:30
sabaimran
3e7e73ddd6 Switch from using dynamic routes to static routes and extracting slug from URL manually. See https://github.com/vercel/next.js/discussions/64660 for limitations with static export / dynamic routes 2024-07-11 23:06:27 +05:30
sabaimran
bea0aa5445 Improve the logged out share experience 2024-07-11 20:11:21 +05:30
Debanjum Singh Solanky
cbae8b68fb Add DB migration from making bi_encode configs optional in #834 2024-07-11 16:33:31 +05:30
Debanjum Singh Solanky
3a75838196 Add Keyboard shortcuts to navigate in Khoj Desktop 2024-07-11 16:29:53 +05:30
Debanjum Singh Solanky
6c1861b319 Improve the prompt to generate images with DALLE3 and SD3
- Major
  - Ask for prompt in prose
  - Remove seed from SD3 image generation to improve diversity of output
    for a given prompt
    Otherwise for conversations with similar sounding
    prompts, the images would be almost exactly the same. This maybe
    another indicator of SD3's inability to capture detailed
    instructions
  - Consistently use "prompt" wording instead of "query" in improved
    image generation prompts.
    Previously a mix of those terms were being used, which could confuse
    the chat model

- Minor
  - Add day of week to prompt
  - Remove 2-5 sentence limit on instructions to SD3. It seems to be
    able to follow longer instructions just with less fidelity than
    DALLE. And the 2-5 sentence instruction limit wasn't being adhered to
  - Improve ability to edit, improve the image based on follow-up
    instructions by the user
  - Align prompts for DALLE and SD3. Only difference is to wrap text to
    be rendered in quotes for SD3. This improves it's ability to render
    requested text. DALLE cannot render text as well or consistently
2024-07-11 16:29:53 +05:30
Debanjum Singh Solanky
21fe1a917b Support syncing, searching images from Obsidian plugin 2024-07-11 16:22:31 +05:30
sabaimran
6f1d799759 Modularize code and implemenet share experience 2024-07-10 23:08:16 +05:30
sabaimran
1b4a51f4a2 Remove print statement for debugging timestamps 2024-07-10 14:54:22 +05:30
sabaimran
0369eb6e0e Fix timestamp bug for pending message and expand CSP for thumbnails 2024-07-10 14:53:31 +05:30
sabaimran
375685530f Add content security policy to the chat page 2024-07-10 11:18:41 +05:30
sabaimran
c5cfd0f2cf Remove unused slash command-related useeffect hook 2024-07-10 10:03:58 +05:30
sabaimran
e1a5c17775 Add DOMPurify for rendering md text. Add a easter egg in the console 2024-07-10 10:03:08 +05:30
sabaimran
e358723baa Fix image rendering and unique key for pending message? 2024-07-09 21:55:54 +05:30
sabaimran
c8c5d50b1a Improve command bar slash experience 2024-07-09 21:39:13 +05:30
sabaimran
c25bf97831 Update hover styling for see all button 2024-07-09 20:55:54 +05:30
sabaimran
23b71b0dff Remove shadow from the slash command bar 2024-07-09 20:52:38 +05:30
sabaimran
998e2aec30 Update dark mode, fix chat message time stamp, fix rendering for new message 2024-07-09 20:50:20 +05:30
sabaimran
0c6b6de09e Revert web client route chat page rendering logic 2024-07-09 19:47:04 +05:30
sabaimran
cc22e1b013 Add pop-up module for the slash commands 2024-07-09 19:46:17 +05:30
sabaimran
5b69252337 Add hover effects for chat messages 2024-07-09 14:56:57 +05:30
sabaimran
a0e9530fa4 Merge branch 'master' of github.com:khoj-ai/khoj into features/chat-ui-updates-big 2024-07-09 12:57:50 +05:30
sabaimran
4471c1e37f Apply mitigations for piling up open connections
- Because we're using a FastAPI api framework with a Django ORM, we're running into some interesting conditions around connection pooling and clean-up. We're ending up with a large pile-up of open, stale connections to the DB recurringly when the server has been running for a while. To mitigate this problem, given starlette and django run in different python threads, add a middleware that will go and call the connection clean up method in each of the threads.
2024-07-09 12:22:58 +05:30
sabaimran
609e7ee19c Fix width of side panel 2024-07-09 12:02:01 +05:30
sabaimran
bf4c2f219e Merge branch 'master' of github.com:khoj-ai/khoj into features/chat-ui-updates-big 2024-07-08 17:00:42 +05:30
Debanjum Singh Solanky
9e31ebff93 Release Khoj version 1.16.0 2024-07-07 18:26:10 +05:30
Debanjum Singh Solanky
54132efd67 Fix Khoj Obsidian plugin build 2024-07-07 18:26:10 +05:30
Debanjum Singh Solanky
510d9b3a29 Add short keys to open chat menu, new chat, search from Obsidian pane 2024-07-07 17:57:17 +05:30
Debanjum Singh Solanky
3e0c882e27 Transcribe only when keyboard shortcut or button pressed in Obsidian
- Transcribe on holding Ctrl+s keyboard shortcut
- Transcribe on holding the transcribe button pressed via mouse too
- Make the transcribe button robust to inadvertent touches by using timeout
- Do not transcribe, trigger auto-send on silences. Silence detection
  is super rudimentary, just blocks standard emanations by whisper
  when no speech
2024-07-07 17:57:17 +05:30
sabaimran
0eb000c3ea Add health checks for the django ORM 2024-07-07 16:11:28 +05:30
sabaimran
6f8a65c529 References, mobile friendly chat sessions and file filter 2024-07-07 15:42:29 +05:30
Debanjum Singh Solanky
a31cd0dec1 Fix async batch delete of indexed entries 2024-07-06 22:45:26 +05:30
Debanjum
08b379c2ab
Fix, Improve Indexing, Deleting Files (#840)
### Fix
- Fix degrade in speed when indexing large files
- Resolve org-mode indexing bug by splitting current section only once by heading
- Improve summarization by fixing formatting of text in indexed files

### Improve
- Improve scaling user, admin flows to delete all entries for a user
2024-07-06 19:52:42 +05:30
Debanjum Singh Solanky
d693baccbc Make it optional to set the encoder, cross-encoder configs via admin UI 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
1baebb8d0e Identify markdown headings by any whitespace character after ^#+
Previously only markdown headings with space characters after # would
be considered a heading. So ^##\t wouldn't be considered a valid heading
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
010486fb36 Split current section once by heading to resolve org-mode indexing bug
- Split once by heading (=first_non_empty) to extract current section body
  Otherwise child headings with same prefix as current heading will
  cause the section split to go into infinite loop
- Also add check to prevent getting into recursive loop while trying
  to split entry into sub sections
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
6a135b1ed7 Fix degrade in speed of indexing large files. Improve summarization
Adding files to the DB for summarization was slow, buggy in two ways:
- We were updating same text of modified files in DB = no of chunks
  per file times

- The `" ".join(file_content)' code was breaking each character in the
  file content by a space. This formats the original file content
  incorrectly before storing in the DB

Because this code ran in the main file indexing path, it was slowing down
file indexing. Knowledge bases with larger files were impacted more strongly
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
e6ffb6b52c Improve scaling user flow to delete all entries
- Delete entries by batch to improve efficiency of query at scale
- Share code to delete all user entries between it's async, sync methods
- Add indicator to show when files being deleted on web config page
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
1ab59865b5 Improve scaling admin flow to delete all entries for user 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
9bdb48807b Ratelimit text to speech model. Validate share chat url domain
- Do not log auth error message on server when Resend setup as Magic
  links for sign-in are now supported
2024-07-06 12:53:19 +05:30
Debanjum Singh Solanky
b334db0fca Add CSP to web config pages. Load phone no validation js, css from S3 2024-07-06 12:48:28 +05:30
Debanjum Singh Solanky
2f034f807a Construct config page elements on Web via DOM scripting.
Minimize isage of innerHTML to prevent DOM clobbering and unintended
escape by user Input
2024-07-06 12:48:28 +05:30
Debanjum Singh Solanky
69c9e8cc08 Disable CSP in Khoj Obsidian as it interferes with Obsidian functionality
The Khoj CSP interferes with other Obsidian features and plugins as
CSP is applied page wide.

For now chat message sanitization via Dompurify should suffice.

Enable CSP when can scope it to only the Khoj Obsidian plugin.
2024-07-05 16:10:08 +05:30
Debanjum Singh Solanky
a353d883a0 Make it optional to set the encoder, cross-encoder configs via admin UI
Upgrade sentence-transformer, add einops dependency for some sentence
transformer models like nomic
2024-07-05 16:09:30 +05:30
Debanjum Singh Solanky
6d59ad7fc9 Add listening circle animation to speak button in Obsidian plugin
Use icon active focus as color of animation button
2024-07-05 14:00:53 +05:30
sabaimran
aec44a0b89 Add dark mode toggle! And improve experience for train of thought 2024-07-04 18:29:21 +05:30
Debanjum Singh Solanky
516af86575 Fix add, remove of the text to speech loader element in Obsidian 2024-07-04 17:38:45 +05:30
sabaimran
465ef0b772 Add a loading experience when waiting for khoj response 2024-07-04 13:49:51 +05:30
Debanjum Singh Solanky
814aca6d69 Skip summarize when not triggered via slash cmd and can't summarize
Maybe better to fallback to non-summarize behavior if summarize intent
is just inferred but we can't actually summarize because the single
file added to conversation isn't satisfied
2024-07-04 13:31:00 +05:30
Debanjum
4446de00d3
Enable Voice, Keyboard Shortcuts in Khoj Obsidian Plugin (#837)
- Simplify quick jump between Khoj side pane and main editor view using keyboard shortcuts
- Enable voice chat in Obsidian to make interactions with Khoj more seamless
2024-07-04 13:28:29 +05:30
sabaimran
5ea8b16f84 Fix missing method error 2024-07-04 12:08:22 +05:30
sabaimran
d61bddf56c Fix retrieving image model by prefetching the openai config in the async method 2024-07-04 11:58:33 +05:30
sabaimran
a129b017b9 Fix image generation on server -- use default config when not set by user 2024-07-04 09:13:23 +05:30
sabaimran
34118078bf kill the emojis 2024-07-04 00:30:21 +05:30
sabaimran
d5ba916978 Working example of streaming, intersection observer, other UI updates 2024-07-04 00:30:01 +05:30
sabaimran
78d1a29bc1 Finish up filte filter side panel menu 2024-07-02 23:32:36 +05:30
sabaimran
6fa2dbc042 Do not use the custom configured max prompt size to send message to anthropic 2024-07-02 21:59:06 +05:30
sabaimran
8a6722ba97 Add basic implementation for chat side panel components 2024-07-02 21:56:43 +05:30
Debanjum Singh Solanky
afcfc60637 Merge DB migrations post merge of SD3 via API support PR 2024-07-02 17:54:58 +05:30
Debanjum
c015eeb5dd
Improve Online Search: Parallelize Search, Use Jina Reader API by default (#832)
- Overview
  Khoj wil be able to do online search out of the box, even for self-hosted users
  - Default to Jina search, reader API when no Serper.dev, Olostep API keys
  - Run online searches in parallel to process multiple queries faster

- Details
  - Jina provides a [reader API](https://github.com/jina-ai/reader) for online search and web page reading
     It requires no API key. This provides a good default to enable 
     online search for self-hosted readers requiring no additional setup. 

  - Jina search API also returns webpage contents with the results, so
     just use those directly when Jina Search API used instead of
     trying to read webpages separately. The extract relevant content from
     webpage step using a chat model is still used from the
    `read_webpage_and_extract_content' func in this case.

  - Parse search results from Jina search API into same format as
     Serper.dev for accurate rendering of online references by clients

  - Run online searches in parallel with AsyncIO to process multiple queries faster
2024-07-02 17:44:51 +05:30
Debanjum
826c3dc9cc
Enable using Stable Diffusion 3 for Image Generation via API (#830)
- Support Stable Diffusion 3 via API
  Server Admin needs to setup model similar to DALLE-3 via Django Admin Panel
- Use shorter prompt generator to prompt SD3 to create better images
- Allow users to set paint model to use from web client config page
2024-07-02 17:28:50 +05:30
Debanjum Singh Solanky
553beae848 No need to set OpenAI API key from environment variable explicitly
It is unnecessary as the OpenAI client automatically tries to use API
key from OPENAI_API_KEY env var when the api_key field is unset
2024-07-02 17:19:09 +05:30
Debanjum Singh Solanky
a038e4911b Default to Jina search, reader API when no Serper.dev, Olostep API keys
Jina AI provides a search and webpage reader API that doesn't require
an API key. This provides a good default to enable online search for
self-hosted readers requiring no additional setup.

Jina search API also returns webpage contents with the results, so
just use those directly when Jina Search API used instead of
trying to read webpages separately. The extract relvant content from
webpage step using a chat model is still used from the
`read_webpage_and_extract_content' func in this case.

Parse search results from Jina search API into same format as
Serper.dev for accurate rendering of online references by clients
2024-07-02 17:19:08 +05:30
Debanjum Singh Solanky
ff44734774 Run online searches in parallel to process multiple queries faster 2024-07-02 17:19:08 +05:30
sabaimran
0ee7cc8c47 Change overall architecure of how information is flowing for better statefulness 2024-07-02 12:39:54 +05:30
sabaimran
541ce04ebc Checkpoint: Updated sidebar panel with new components
- Add non-functional UI elements for chat, references, feedback buttons, rename/share session, mic, attachment, websocket connection
2024-07-02 11:18:50 +05:30
Raghav Tirumale
8eccd8a5e4
Support Indexing Images via OCR (#823)
- Added support for uploading .jpeg, .jpg, and .png files to Khoj from Web, Desktop app
- Updating indexer to generate raw text and entries using RapidOCR
- Details
  * added support for indexing images via ocr
  * fixed pyproject.toml
  * Update src/khoj/processor/content/images/image_to_entries.py
     Co-authored-by: Debanjum <debanjum@gmail.com>
  * Update src/khoj/processor/content/images/image_to_entries.py
     Co-authored-by: Debanjum <debanjum@gmail.com>
  * removed redudant try except blocks
  * updated desktop js file to support image formats
  * added tests for jpg and png
  * Fix processing for image to entries files
  * Update unit tests with working image indexer
  * Change png test from version verificaition to open-cv verification

---------

Co-authored-by: Debanjum <debanjum@gmail.com>
Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-07-01 06:00:00 -07:00
Debanjum Singh Solanky
cffc14a46a Trigger voice chat via keyboard shortcut in Khoj side pane
Quickly trigger voice chat from Khoj side pane using Keyboard shortcuts
2024-07-01 18:06:09 +05:30
Debanjum Singh Solanky
3723904512 Toggle jump between Khoj side pane & previous editor via cmd, kbd shortcut
Improve quick navigation to, from Khoj side pane using Keyboard
shortcut or Obsidian command
2024-07-01 18:05:59 +05:30
Debanjum Singh Solanky
fbb95ca342 Put cursor on chat input when focus on chat view in Obsidian
This should improve fluidity of keyboard interactions with Khoj on
Obsidian.

Open Khoj chat view via keybinding or command pallete and ask
question using only the keyboard, with no mouse clicks required
2024-07-01 18:05:55 +05:30
Debanjum Singh Solanky
093e276908 Enable Voice chat in Khoj Obsidian plugin
- Automatically carry out voice chats with Khoj from within Obsidian
  When send voice message, Khoj will auto respond with voice as well
- Listen to past Khoj messages as speech
- Add circular loading spinner to use while message is being converted
  to speech
2024-07-01 18:02:28 +05:30
sabaimran
c83b8f2768
Allow just one worker to be the background schedule leader (#836)
* Add a leader election mechanism to circumvent runtime issues for multiple schedulers

- Reduce the load on the DB and risk of issues on the service side by limiting the execution environment to one elected leader at a given time. This one is responsible for managing all of the execution of the jobs, though all workers are capable of adding and removing jobs

* Set a max duration for the schedule leader position (12 hrs), add some error if automation not added successfully
2024-06-28 13:13:25 +05:30
sabaimran
80fe5ce182 Fix user not authenticated interpretation error 2024-06-27 21:13:54 +05:30
Raghav Tirumale
24a0d8b073
Add OS Level Shortcut Window for Quick Access to Khoj Desktop (#815)
* rough sketch of desktop shortcuts. many bugs to fix still

* working MVP of desktop shortcut khoj

* UI fixes

* UI improvements for editable shortcut message

* major rendering fix to prevent clipboard text from getting lost

* UI improvements and bug fixes

* UI upgrades: custom top bar, edit sent message and color matching

* removed debug javascript file

* font reverted to Noto Sans

* cleaning up the code and removing diffs

* UX fixes

* cleaning up unused methods from html

* front end for button to send user back to main window to continue conversation

* UX fix for window and continue conversation support added

* migrated common js functions into chatutils.js

* Fix window closing issue in macos by

1. Use a helper function to determine if the window is open by seeing if there's a browser window with shortcut.html loaded
2. Use the  event listener on the window to handle teardown

* removed extra comment and renamed continue convo button

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-06-27 07:20:13 -07:00
sabaimran
870d9ecdbf
Add a fact checker feature with updated styling (#835)
- Add an experimental feature used for fact-checking falsifiable statements with customizable models. See attached screenshot for example. Once you input a statement that needs to be fact-checked, Khoj goes on a research spree to verify or refute it.
- Integrate frontend libraries for [Tailwind](https://tailwindcss.com/) and [ShadCN](https://ui.shadcn.com/) for easier UI development. Update corresponding styling for some existing UI components. 
- Add component for model selection 
- Add backend support for sharing arbitrary packets of data that will be consumed by specific front-end views in shareable scenarios
2024-06-27 18:45:38 +05:30
sabaimran
3b7a9358c3
Add our first view via Next.js for Agents (#817)
Initialize our migration to use Next.js for front-end views via Agents. This includes setup for getting authenticated users, reading in available agents, setting up a pop-up modal when you're clicking on an agent, and allowing users to start new conversations with agents.

Best attempt at an in-place migration, though there are some noticeable differences.

Also adds view for chat that are not being used, but in experimental phase.
2024-06-27 13:56:16 +05:30
Debanjum Singh Solanky
afbeee9e82 Rename copy-button to more general chat-action-button in Obsidian client
- Use 4 space indent of activateView function in pane_view component
2024-06-26 18:09:23 +05:30
sabaimran
8c12a69570 Fix issue in anthropic chat when khoj message becomes top message
This is because Anthropic requires the first message in the chat history to be from the user.
2024-06-26 12:59:34 +05:30
Debanjum Singh Solanky
4f89319b40 Release Khoj version 1.15.0 2024-06-26 10:38:16 +05:30
Debanjum Singh Solanky
c793d8a69e Add Validation logic to save PaintModel. Use API key from Paint Model
Rename Paint Model, Adapters to TextToImage for consistency
2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
1acf969c6e Do not require OpenAI to generate image as local chat + sd3 works now
Previously the text_to_image helper would only trigger the image
generation flow if OpenAI client was setup. This is not required
anymore as offline chat model + sd3 API works. So remove that check
2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
2c4bf91a61 Allow user to set paint model to use from web client config page 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
eb09aba747 Remove quotes wrapping the prompt from being passed to image gen model 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
fdd4c02461 Use shorter prompt generator to prompt SD3 to create better images 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
eda33e092f Enable using Stable Diffusion 3 for Image Generation via API 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
cfe46fd9f5 Add Border Color instead of BG Color for Chat Message in Obsidian 2024-06-26 08:11:04 +05:30
sabaimran
fb818ead60 Use active bg instead of code background for khoj response 2024-06-26 08:05:13 +05:30
sabaimran
a4b2552540 Update conversation session selection menu to use Obsidian theme colors as well 2024-06-26 08:05:13 +05:30
sabaimran
da5b07e913 Remove custom styling on the reference buttons 2024-06-26 08:05:13 +05:30
sabaimran
c4a1ae9375 Make the Khoj Obsidian plugin more user theme friendly
Use the CSS variables from the theme for the Khoj UI components
2024-06-26 08:04:17 +05:30
Debanjum Singh Solanky
d6fe5d9a63 Pass current component as arg to markdown renderer in chat view
This doesn't work on search modal, but hopefully will get resolved
once we migrate search into a view from a modal
2024-06-24 16:12:20 +05:30
Debanjum Singh Solanky
732332a3c5 Spell fix s/e.g/e.g./ across code, tests and docs 2024-06-24 15:24:45 +05:30
Debanjum Singh Solanky
8fc7f980aa Revert KHOJ_DOMAIN to only support single domain.
Multiple domain support didn't generalize to other portions where it
is used
2024-06-24 15:24:45 +05:30
sabaimran
939811e9b5 Fix conversation look up logic 2024-06-24 09:10:03 +05:30
Debanjum Singh Solanky
a4d88612c1 Just use yarn for package version locking. Remove npm package lock 2024-06-23 16:06:20 +05:30
Debanjum Singh Solanky
55be90cdd2 Sanitize user input fields on Automations page of web client
Use Dompurify to sanitize user input
2024-06-23 14:14:47 +05:30
Debanjum Singh Solanky
1c7a562880 Generate automation cards via DOM scripting 2024-06-23 13:22:38 +05:30
Debanjum Singh Solanky
c7c32a7467 Improve online chat reference extraction in Khoj.el Emacs package
- Handle online references with no title
- Improve handling references which are arrays instead of lists
2024-06-23 08:13:36 +05:30
Debanjum Singh Solanky
9d33d8c0fa Upgrade typescript eslint dev dependency of Khoj Obsidian plugin 2024-06-23 07:36:49 +05:30
Debanjum
a94062469a
Automatically Find Similar Notes on Emacs in Background (#827)
Khoj will find and display notes similar to the current entry in the side pane when
1. find similar is open in side pane and
2. cursor has moved to a new entry

### Major
- Find similar notes to current note at cursor automatically in background
- Only show headings of search result and increase default results count

### Minor
- Pass absolute path of file to index from khoj.el emacs client
- Update help message to only show the smaller set of new keybindings
- Fix edge cases in loading some chat sessions
2024-06-23 07:36:11 +05:30
sabaimran
a53178cab9
Add developer support for using next.js to serve generated static files (#814)
To improve the developer experience for front-end development, we're migrating to Next.js. In order to do this migration page-by-page, we're using static site generation via Next.js. This also helps us avoid making cross site requests from front-end to back-end for the time being, while giving a ramp to separating out server and client if needed for scale down the road.

Dev instructions for using the next.js setup are in the added README.

This adds scaffolding for including the built files in the python package as well as the docker images. Docker setup has been tested locally. In order to verify the build is working as expected, we can navigate to the {khoj_host}:42110/experimental and verify that the experiment page comes up.

This setup works with serving static files included in the src/interface/web folder from the Django app. The key bit for understanding the setup is in the yarn export command in package.json.
2024-06-22 20:12:41 +05:30
Debanjum Singh Solanky
abd6f58aee Upgrade Desktop app package dependencies 2024-06-22 17:38:52 +05:30
Debanjum Singh Solanky
f413dc62cd Upgrade Obsidian plugin dependencies. Add package lock file for it
Add it to bump_version script as well.
2024-06-22 17:38:52 +05:30
Debanjum Singh Solanky
7e277e9381 Fix getting file-toggle-button element in chat of web app 2024-06-21 15:54:38 +05:30
Debanjum Singh Solanky
fa7b40ab86 Automatically respond with Voice if subscribed user sent Voice message 2024-06-21 15:53:01 +05:30
Debanjum Singh Solanky
5e5fe4b7af Improve font size, spacing of conversation session on desktop app 2024-06-21 12:25:35 +05:30
sabaimran
d3c0111121 Include base URL when using openai api config in extract questions. Close #831 2024-06-21 12:18:50 +05:30
sabaimran
b9966eb3d4
Add support for text to speech in chat responses (#821)
* Enable speech to text responses in khoj chat

- Current issue: reads out all the markdown formatting, plus waits for the whole result to be streamed before playing it

* Extract content from markdown-formatted text

* Add a loader for while you're waiting for Khoj's response

* Add user configuration option for chat model options, allow server side configuration for option list

* Join up APIs, views, admin pages to allow configuring custom voice models
2024-06-21 11:30:28 +05:30
Debanjum Singh Solanky
427575e958 Improve khoj chat new, delete session flows
When create new conversation session, automatically request query. As
that is expected next action after creating new session

Pass session-id to khoj-chat to allow reuse from
create-new-conversation func

When delete conversation session, do not call load chat session.
Unnecessary action.

Use thread-last to improve code flow in new, delete conversation funcs
2024-06-21 10:54:59 +05:30
Debanjum Singh Solanky
59032a06d5 Improve defaults when extracting fields from online reference in khoj.el 2024-06-21 10:54:59 +05:30
Debanjum Singh Solanky
9262aea7a5 Fix comments, func calls based on melpazoid, checkdoc, package-lint 2024-06-21 10:54:59 +05:30
sabaimran
ff26b19d2b Add a migration for allowing the docx field in the entries file type 2024-06-21 09:47:49 +05:30
sabaimran
3cfe5aabe5
Add support for magic link email sign-in (#820)
* Add magic link email sign-in option

* Adding backend routes and model changes to keep state of email verification code and status

* Test and fix end to end email verification flow

* Add documentation for how to use the magic link sign-in when self-hosting Khoj

* Add magic link sign in to public conversation page
2024-06-20 13:32:58 +05:30
Debanjum Singh Solanky
0afe66ac39 Restore cursor to original window after opening Khoj side pane
Previously the cursor would move to the Khoj side pane on opening it.
This would break user's flow, especially when find similar triggers
automatically

New behavior maintains smoother update of auto find similar without
disrupting user browsing
2024-06-20 12:50:13 +05:30
Debanjum Singh Solanky
afe91a2633 Only show headings of search result and increase total count returned
Previously it would show complete result body this would make the
result width variable and hard to track all the returned results

Showing just heading makes it easier to track
2024-06-20 12:50:13 +05:30
Debanjum Singh Solanky
2b12a5514e Find similar notes to current note at cursor automatically in background
- Call find similar on current element if point has moved to new
  element
- Delete the first result from find-similar search results as that'll
  be the current note (which is trivially most similar to itself)
- Determine find-similar based text formating at the rendering layer
  rather than at the top level find-similar func
2024-06-20 12:50:13 +05:30
Raghav Tirumale
bd3b590153
Support Indexing Docx Files (#801)
* Add support for indexing docx files and associated unit tests

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-06-20 11:18:01 +05:30
Debanjum Singh Solanky
d042e073cc Pass absolute path of file to index from khoj.el emacs client 2024-06-20 00:26:18 +05:30
Debanjum Singh Solanky
d23f2849d4 Update help message to only show the smaller set of new keybindings 2024-06-20 00:26:18 +05:30
Raghav Tirumale
d4e5c95711
Add Ability to Summarize Documents (#800)
* Uses entire file text and summarizer model to generate document summary.
* Uses the contents of the user's query to create a tailored summary.
* Integrates with File Filters #788 for a better UX.
2024-06-18 19:31:07 +05:30
Debanjum Singh Solanky
677d49d438 Release Khoj version 1.14.0 2024-06-18 17:13:46 +05:30
Debanjum Singh Solanky
2930b57c78 Use hashed value to improve deduplication of search results on server 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
6814dadd21 Fix opening Web, Desktop setup links on first run from Desktop app
Previous version failed to open the setup links
2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
632f55a9e8 Do not default to rerank if device has GPU 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
f1120f24a1 Use solarized light css styling to highlight code in chat messages 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
d8a5a01cea Pass multiple allowed Khoj domains via KHOJ_DOMAIN env var
To add multiple allowed Khoj domains pass them as a comma separated
list of domains via the KHOJ_DOMAIN environment variable

Resolve comment in issue #662
2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
4daf16e5f9 Only redirect to next url relative to current domain 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
86a3505d89 Remove image HTML elements from non whitelisted sources in Obsidian chat
Given img src enforcement via CSP required loosening. Soft enforce it
via a regex replace of img HTML elements if the src isn't from the
whitelisted set of source prefixes.

Currently allowed source prefixes are
- app: for local images
- data: for inline generated images
- https://generated.khoj.dev: for cloud generated images
2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
c7d825bddb Sanitize markdown in Obsidian after conversion to HTML too
- Create and use a function to convert markdown to sanitized html
- Remove unused Latex delimiter handling as Katex isn't used in
  Khoj chat on Obsidian
2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
08c3aa496d Loosen CSP in Obsidian to load images, sync and allow Obsidian domain 2024-06-18 17:04:25 +05:30
sabaimran
ba0187798a Get converastion id before retrieving relevant notes in non-socket code 2024-06-17 14:26:06 +05:30
Debanjum
d2d9f4888e
Upgrade Khoj Emacs UX (#812)
- Open Khoj in Emacs Side pane
   Open Khoj chat, search in right pane to allow for ambient engagement
- Improve Khoj Chat
  - Show online references used for chat
  - Make chat API call async to not block user interactions
  - Fix loading chat history, references in khoj.el chat buffer
- Improve Khoj Search, Find Similar functions
   - Make calls to Khoj search API async to not block user interactions
- Support Conversation Sessions
  - Create transient menu to open, create, delete conversation sessions from the Khoj Emacs client
2024-06-16 10:39:48 +05:30
Debanjum Singh Solanky
fe36adb7b9 Remove short keys to switch content type during search to avoid conflict
- C-x o to switch to search org content conflicts with switch buffer shortkey
  This is more apparent in the async search scenario as it prevents
  perform other actions while async search is in progress

- Also switching content type wouldn't scale to all the content types
  Khoj will support without causing more conflicting keybinding
2024-06-15 17:31:19 +05:30
Debanjum Singh Solanky
2a84524d19 Make khoj.el search, similar API calls async to not block user interactions 2024-06-15 17:30:58 +05:30
Debanjum Singh Solanky
c6b95f8776 Handle rendering messages using the old reference schema in khoj.el
Previously references were a list instead of a map
2024-06-15 17:30:58 +05:30
Debanjum Singh Solanky
db056c896d Delete old conversation sessions from the chat menu in Khoj Emacs 2024-06-15 17:30:58 +05:30
Debanjum Singh Solanky
e3d995a74f Extract select conversation session logic into func for reusability 2024-06-15 17:30:38 +05:30
Debanjum Singh Solanky
e15dc23bbe Improve logic to create vs reuse window for khoj side pane logic
Khoj side pane occupies a vertically split bottom right side pane.
If the bottom right window is not a vertical split, create a new
vertical split pane for khoj, otherwise reuse the existing window
2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
055e5e8d26 Create new conversation from the chat menu in Khoj Emacs 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
c33954cd93 Fix loading an empty chat session in Emacs 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
e21c0648ae Create, use reusable function to call Khoj API from elisp 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
7bcb49b6e7 Support conversation sessions in the Khoj Emacs client
Add option in khoj main transient menu option to open menu to
- switch between existing conversations
2024-06-15 13:13:20 +05:30
Debanjum Singh Solanky
df9c5ff263 Show online references used for chat response as footnotes in Emacs
Previously online references used weren't being shown
2024-06-15 13:13:19 +05:30
sabaimran
25d8cdd9cd Misc fixes:
- Fix getting file filters for not found conversations
- Allow iamge rendering in automation emails
- Fix nearest 15th minute calculation in automations creation
2024-06-14 16:20:22 +05:30
Raghav Tirumale
35715096f4
UX Improvement: Keyboard Shortcuts for Recent Messages (#804)
* added keyboard shortcuts to access old queries
2024-06-14 12:45:09 +05:30
sabaimran
2dcfb3c2f0 Fix bug for drag and drop single file 2024-06-14 12:01:10 +05:30
sabaimran
7e4a61f2ac Disable rate limiting if billing is not enabled 2024-06-12 21:39:02 +05:30
Debanjum Singh Solanky
385057f09e Make khoj.el chat API call async to not block user interactions 2024-06-12 21:04:48 +05:30
sabaimran
45e725ac9c Use the summarizer model for generating improved image prompts 2024-06-12 17:41:12 +05:30
Raghav Tirumale
673d0d367c
Fix: Adding Support for Uploading Multiple Files (#803)
* added support for uploading multiple files at a time.

* optimized multiple file upload to use a batch upload

* allowing files to upload even if there is one unsupported file
2024-06-12 15:51:35 +05:30
Debanjum Singh Solanky
906ebee075 Open Khoj chat, search in right pane to allow for ambient engagement
See the currently active window in context while doing chat, search
or find similar operations in a side pane.

This is similar to how we've moved Khoj on Obsidian into the side pane
as well
2024-06-09 23:32:34 +05:30
Debanjum Singh Solanky
cd4baa3fa5 Fix loading chat history, references in khoj.el chat buffer 2024-06-09 18:34:00 +05:30
Debanjum
6afbd8032e
Improve Intermediate Steps in Formulating Chat Response (#799)
# Major
- Disambiguate Text output mode to disambiguate from Default data source lookup
- Fix showing headings in intermediate step in generating chat response
- Remove "Path" prefix from org ancestor heading in compiled entry

# Minor
- Fix OpenAI chat actor, director unit tests
2024-06-09 07:55:01 +05:30
sabaimran
2e209ab28b Handle case where conversation does not (yet) exist 2024-06-08 16:22:12 +05:30
sabaimran
849c38c0a4 Add support for managing audiences for new users 2024-06-08 15:51:17 +05:30
sabaimran
06a47ee457
Add language-specific syntax highlighting via highlight.js (#802)
* Add language-specific syntax highlighting via highlight.js

- Add highlight.js to our assets CDN for fast load and compliance with the CSP
- See other stylesheets options here: https://cdnjs.com/libraries/highlight.js

* Bonus: set min-height to prevent increasing length of the sessions pane

* Fix references rendering and add highlight.js in public conversation
2024-06-08 15:17:09 +05:30
sabaimran
dbb06466bf Minor fit/finish updates to the file filter experience 2024-06-07 15:05:00 +05:30
sabaimran
58a02f06ea
Fix multilingual font rendering (#797)
* Fix multilingual font rendering; fallback to an Arabic language font which contains more Asian characters. Close #756

* Tune font-sizes and styling to accomodate new fonts with old sizing

- Move connection-status styling out from inline html into css block
- Remove start typing chat-input height jitter
- align new-conversation button, text
- use relative font sizes instead of absolute font sizes in most places

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
2024-06-07 11:53:47 +05:30
Raghav Tirumale
ba16afd3c2
New Feature: Adding File Filtering to Conversations (#788)
* UI update for file filtered conversations
* Interactive file menu #UI to add/remove files on each conversation as references.
* Backend changes implemented to load selected file filters from a conversation into the querying process.
---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-06-07 10:53:37 +05:30
Debanjum Singh Solanky
f91cdf8e18 Fix showing headings in intermediate step in generating chat response 2024-06-06 16:52:23 +05:30
Debanjum Singh Solanky
18f7e6e7ed Remove "Path" prefix from org ancestor heading in compiled entry 2024-06-06 16:51:26 +05:30
sabaimran
8d701ebe22
Add fedCM to accommodate google migration (#798)
- See migration guidelines here: https://developers.google.com/identity/gsi/web/guides/fedcm-migration#fedcm_flag
2024-06-06 14:23:16 +05:30
Debanjum Singh Solanky
dd2225b1aa Use Text output mode to disambiguate from Default data source lookup
Previously if default output was selected by Khoj, we'd end up doing
an documents search as well, even when Khoj selected internet or
general data source to lookup.

This update disambiguates the default information mode from the text
output mode. To avoid doing documents search when not deemed necessary
by Khoj
2024-06-06 11:56:48 +05:30
Debanjum Singh Solanky
a1e4f4bde7 Gracefully skip indexing when empty list of docs provided
Improve error message when fail to index content
2024-06-05 19:39:15 +05:30
Debanjum Singh Solanky
21987f60c7 Use `-difference' to get files to delete. Make batch size defcustom
Improve docstrings to align with `checkdoc' requirement for all args
being mentioned
2024-06-05 19:39:15 +05:30
Debanjum
bfacd65971
Batch upload files for indexing from the Emacs client (#735) from yuzhou721/master
Encode filenames and batch file uploads to improve sending content to index from the Emacs client
2024-06-05 19:31:06 +05:30
sabaimran
a9c383e62c Use an ASGI application, rather than WSGI
- ASGI should be the preferred application, as our codebase runs a lot of async code
2024-06-05 09:25:08 +05:30
sabaimran
0816cec4bc Manually close old db connections periodically 2024-06-04 22:19:47 +05:30
sabaimran
acfdc8da77 Explicitly set the connection age to 0 in the django settings. Seems to be some strange behavior with async gunicorn + django db 2024-06-04 20:31:51 +05:30
Debanjum Singh Solanky
85a343363b Release Khoj version 1.13.0 2024-06-04 11:57:44 +05:30
Debanjum Singh Solanky
b757ba664f Sanitize chat messages to render in Obsidian, Desktop, Web apps
Use DOMPurify to escape any unsafe HTML in chat message before adding
it to DOM via innerHTML updates to a HTML element
2024-06-04 10:53:30 +05:30
Debanjum Singh Solanky
9f80c2ab76 Enforce Content-Security-Policy (CSP) in Obsidian, Desktop, Web apps
Prevent XSS attacks by enforcing Content-Security-Policy (CSP) in apps.
Do not allow loading images, other assets from untrusted domains.

- Only allow loading assets from trusted domains
  like 'self', khoj.dev, ipapi for geolocation, google (fonts, img)
  - images from khoj domain, google (for profile pic)
  - assets from khoj domain
  - Do not allow iframe src
  - Allow unsafe-inline script and styles for now as markdown-it escapes html
    in user, khoj chat

- Add hostURL to CSP of the Desktop, Obsidian apps
  Given web client is served by khoj server, it doesn't need to
  explicitly allow for khoj.dev domain. So if user self-hosting, it'll
  automatically allow the domain in the CSP (via 'self')

  Whereas the Obsidian, Desktop clients allow configure the server URL.
  Note *switching server URL breaks CSP until app is reloaded*
2024-06-04 10:53:30 +05:30
Debanjum Singh Solanky
bbcdb8413d Add null checks, fix build errors in Khoj plugin on newer Obsidian 2024-06-03 18:03:11 +05:30
Debanjum Singh Solanky
d8ace4d34c Highlight the agents, automation tab when active on the web app 2024-06-03 16:57:03 +05:30
sabaimran
4679f07336 Clean up some of the design of agents, inspired by dicussion #792 2024-06-03 12:52:07 +05:30
Debanjum Singh Solanky
8cdab5f31a Update slash command UX in chat UI of desktop app to match web app
Make commands in popup menu on typing slash in chat input selectable
2024-06-02 17:27:37 +05:30
Debanjum Singh Solanky
7828bd6f2e Hide command popup & focus on chatInput on selecting command in web app
Style command popup cursor and add highlight to indicate using slash
command
2024-06-02 17:27:37 +05:30
Debanjum
cf8c9c2a3d
Serve image assets from Khoj domain, not directly from S3 bucket (#734)
- Serve generated images from Khoj domain instead of directly from AWS S3
- Rename assets URL from Khoj S3 bucket to assets.khoj.dev
2024-06-02 17:24:35 +05:30
sabaimran
5bb3689562 Do not stream responses in the scheduled_chat response 2024-06-02 11:31:15 +05:30
sabaimran
5132b01ab1 Remove intent_type from telemetry update in api_chat 2024-06-02 10:21:38 +05:30
Raghav Tirumale
a3934b3aaa
Improved Command Menu and Help Command (#774)
* The command menu (triggered by "/") now has a clickable list of possible commands, that automatically fill into the chat when pressed.
* The `/help` command now searches `khoj.dev` pages to provide useful assistance to the user.

---------

Co-authored-by: raghavt3 <raghavt3@illinois.edu>
Co-authored-by: sabaimran <65192171+sabaimran@users.noreply.github.com>
2024-06-01 22:33:31 +05:30
sabaimran
89178bcebd Fix formatting issues for task email in mobile 2024-06-01 14:19:12 +05:30
Debanjum
b499b3fe2a
Upgrade Khoj Obsidian: Chat from Side Pane, Stream Intermediate Steps, Copy Message to Clipboard (#736)
### Details
- **Chat with Khoj from right pane on Obsidian**
  - Modal was too ephemeral, couldn't have it open for reference, quick jump to Khoj chat
- **Stream intermediate steps taken by Khoj** for generating response to the chat pane
  Gives more transparency into Khoj 'thinking' process, e.g internet, notes searches performed, documents read etc. 
  The feedback allows us to tune our messages to elicit better responses by Khoj
- Add ability to **copy message to clipboard, paste chat messages directly into current file**
- Jump to **Search**, **Find Similar** functions from navigation bar on the Khoj Obsidian side pane
- Improve spacing, use consistent colors in chat message references and buttons

Resolves #789, #754
2024-06-01 13:29:21 +05:30
sabaimran
8b9c26c468 Remove unused method 2024-06-01 12:54:43 +05:30
sabaimran
5ec641837a
Allow automations to be shareable (#790)
* Updating the API / UI to support sharing of automations
* Allow people to see the automations even when not logged in, and add an overlay effect
* Handle unauthenticated users taking actions
* Support showing pre-filled automation details on the config automations page
* Redirect user to login if they try to add an automation while unauthenticated
2024-06-01 12:44:49 +05:30
Debanjum Singh Solanky
7d7d4cf5c3 Make new chat message text selectable in Obsidian side pane
Resolves #789
2024-06-01 11:01:39 +05:30
Debanjum Singh Solanky
7fb7f200b3 Fix rendering text in chat messages with bulleted lists
Improves #789
2024-06-01 10:51:22 +05:30
Debanjum Singh Solanky
7a93599fe8 Merge branch 'master' into upgrade-khoj-on-obsidian
- Conflicts:
  - src/khoj/interface/web/chat.html
    Use our changes with feedback button changes from master
2024-06-01 10:07:43 +05:30
Debanjum Singh Solanky
92bab9fa61 Get Conversation session action buttons out from under the three dot menu 2024-05-31 20:11:00 +05:30
Debanjum Singh Solanky
7fa42daf89 Render action buttons for new Khoj chat responses in Obsidian
- Dedupe the code to add action buttons to chat messages
- Update the renderIncrementalMessage function to also add the action
  buttons to newly generated chat messages by Khoj
2024-05-31 20:11:00 +05:30
Debanjum Singh Solanky
2d010db83f Toggle chat session view on clicking the Obsidian chat sessions button 2024-05-31 20:11:00 +05:30
Debanjum Singh Solanky
275d4877a6 Fix loading spinner visibility by using contrasting background color
Fix code formating of Khoj chat view in Obsidian
2024-05-31 20:09:24 +05:30
sabaimran
2667ef4544 Refresh the conversation from the db in the websocket flow 2024-05-31 16:15:56 +05:30
sabaimran
fd07abbfc8 Decrease the life of one connection 2024-05-31 15:39:15 +05:30
Debanjum
3090b84252
Disable Minutely Recurrence for Automations (#781)
* Disable automation recurrence at minute level frequency

* Set a max lifetime for django's connections to the db

* Disable any automation that has a non-numeric first digit (i.e., recuring on the minute level)

* Re-enable automations

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-05-31 12:50:19 +05:30
sabaimran
5dca48d9fc Fix setting of conn_max_age variable 2024-05-31 11:07:13 +05:30
sabaimran
76f941f4e5 Revert email from from to sender again in resend API. keeps switching? 2024-05-31 10:30:18 +05:30
sabaimran
b27f59b12b Remove all unused code related to websockets 2024-05-30 11:39:04 +05:30
sabaimran
4b3d3fe7ea /s/sender/from in resend calls 2024-05-30 08:43:46 +05:30
sabaimran
2076543e32 Disable AP Scheduler while performing maintenance 2024-05-30 08:02:59 +05:30
Debanjum Singh Solanky
7823ef09dc Simplify conditional code. Improve logs to track conversion progress 2024-05-29 17:50:07 +05:30
Debanjum Singh Solanky
215db8cab3 Reduce log level of noisy process lock logs 2024-05-29 13:14:44 +05:30
Debanjum Singh Solanky
7b18919564 Tag external links to open in a separate window on the Desktop app
Previously clicking inline links would open the URL directly in the
Desktop app. This was strange and it didn't provide any way to go back
to Khoj desktop app UI from the opened link
2024-05-29 10:12:50 +05:30
Debanjum Singh Solanky
c957a6cb43 Delete unused base_processor_integration html file from web interface 2024-05-29 08:30:13 +05:30
sabaimran
cb33fb67fe Remove the automations-related dead code in the web config 2024-05-29 04:22:45 +05:30
Debanjum Singh Solanky
7594401461 Fix expand chat reference animation in web, desktop, obsidian clients 2024-05-28 20:56:26 +05:30
Debanjum Singh Solanky
1ea7675fc9 View, switch chat sessions from Obsidian chat pane 2024-05-28 20:33:39 +05:30
Debanjum Singh Solanky
e86899eec4 Click on referenced notes by Khoj chat to open it in Obsidian vault
Allow opening Khoj chat references in Obsidian vault if the reference
is a heading or file in the current Obsidian vault
2024-05-28 10:16:40 +05:30
Desmond
70fea6c6b6 fix: delete file request 2024-05-27 14:46:26 +08:00
sabaimran
607534021b Add a link to github in the settings menu, improve styling 2024-05-27 11:39:30 +05:30
Desmond
3f49b5a4ab fix: emacs tests 2024-05-27 10:42:09 +08:00
sabaimran
b97ca9d19d Skip using max_tokens as input to the extract questions step, as that's not used for max_output 2024-05-27 01:23:54 +05:30
sabaimran
9ebf3a4d80 Improve the admin experience, add more metadata to the list_display
- Don't propagate max_tokens to the openai chat completion method. the max for the newer models is fixed at 4096 max output. The token limit is just used for input
2024-05-27 00:49:20 +05:30
sabaimran
01cdc54ad0
Add support for Anthropic models (#760)
* Add support for chatting with Anthropic's suite of models

- Had to use a custom class because there was enough nuance with how the anthropic SDK works that it would be better to simply separate out the logic. The extract questions flow needed modification of the system prompt in order to work as intended with the haiku model
2024-05-26 22:50:34 +05:30
Debanjum Singh Solanky
0f796a79ec Extract function to get link to entry in Obsidian vault for reuse 2024-05-26 18:03:15 +05:30
Debanjum Singh Solanky
e24ca9ec28 Pass file path of each doc reference in references returned by API
- Pass file path of reference along with the compiled reference in
  list of references returned by chat API converts
- Update the structure of references from list of strings to list of
  dictionary (containing 'compiled' and 'file' keys)
- Pull out the compiled reference from the new references data struct
  wherever it was is being used
2024-05-26 18:02:11 +05:30
Debanjum Singh Solanky
ba330712f8 Fix to always pass online results in chat API response 2024-05-26 13:56:55 +05:30
Debanjum Singh Solanky
38d8d2bb56 Show online references used to generate response in Obsidian chat view 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
f495d338eb Modularize render message with references func in web based clients
Simplify, reuse, standardize code to render messages with references
in the obsidian, web and desktop clients. Specifically:

- Reuse function to create reference section, dedupe code
- Create reusable function to generate image markdown
- Simplify logic to render message with references
2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
14a2006c76 Stream steps taken to generate response in Obsidian chat pane
- Setup websocket using Khoj web app as reference.
- Moved the geolocating code to chat view out from the general pane
  view
- Use loading spinner from web instead of the thinking emoji
2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
afcd22d30c Improve spacing, colors of chat message references and buttons
Works better with dark modes. References have more spacing and adhere
to background color of the chat message itself
2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
bd4931e70b Add ability to paste chat messages directly into current file
It'll replace any highlighted text with the chat message or if not
text is highlighted, it'll insert the chat message at the last cursor
position in the active file
2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
032ad3b521 Add ability to copy messages to clipboard from Obsidian Khoj chat 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
57f1c53214 Create Nav bar for Obsidian pane. Use abstract View class for reuse
- Jump to chat, show similar actions from nav menu of Khoj side pane
  - Add chat, search icons from web, desktop app
  - Use lucide icon for find similar (for now)
  - Match proportions of find similar icon to khoj other icons via css, js

- Use KhojPaneView abstract class to allow reuse of common functionality like
  - Creating the nav bar header in side pane views
  - Loading geo-location data for chat context
  This should make creating new views easier
2024-05-26 13:55:22 +05:30
sabaimran
e23c803cee Release Khoj version 1.12.1 2024-05-24 21:42:03 +05:30
sabaimran
0308699849 Use links from assets.khoj.dev to render images in the automations page 2024-05-24 20:18:02 +05:30
sabaimran
3f9c20a399
Make it easier to manage server-level chat settings (#729)
* Add support for server-wide model settings fix web page reading results returning logic
2024-05-24 20:15:18 +05:30
sabaimran
cbbbe2da9a
Add a schedule picker and automations preview func (#747)
* Update suggested automations
* add a schedule picker when creating an automation
* Create a new conversation in flow of the automation scheduling in order to send a preview and deliver more consistent results
* Start adding in scaffolding to manually trigger a test job for an automation
* Add support for manually triggering automations for testing
* Schedule automation asynchronously
* Update styling of the preview button
* Improve admin lookup experience and prevent jobs from being scheduled to run every minute of everyday
* Ignore mypy issues on job info short description
2024-05-24 19:42:47 +05:30
sabaimran
4511c6ae7c Fix bug in chat feedback flow - user message not included during live chat 2024-05-21 14:55:39 -05:00
Desmond
a3c6045328 Merge remote-tracking branch 'origin/master' 2024-05-21 21:55:53 +08:00
Desmond
b0630c1a98 Simplify partition 2024-05-21 21:52:01 +08:00
Raghav Tirumale
d57772f9e7
Add Feedback Buttons on Chat (#721)
### Description and Rationale for Changes
This feature includes thumbs up and thumbs down buttons on Khoj's chat responses that provide automated feedback. When a thumbs up/down button is clicked, the code sends an email to team@khoj.dev with the following:
* user query
* khoj's response
* whether the sentiment of the user was good or bad. 

This is critical in improving Khoj's nondeterministic LLM model for a better user experience.
### List of Changes
* new endpoint in `api_chat.py` (/feedback) that can be used to trigger mail sending).
* thumbs up and thumbs down buttons implemented in `chat.html`
* new function in `routers/email.py` to handle feedback email sending via resend
* `feedback.html` template for a formatted email with the feedback.

---------

Co-authored-by: mythicalcow <mythicalcow@linux.myguest.virtualbox.org>
Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-05-20 16:29:08 -05:00
sabaimran
7feaf34702 Fix capitalization, update suggeted prompt 2024-05-10 02:36:13 -07:00
sabaimran
b545aceb47 Use a simpler example for the sample automation and put schedule on top of instructions 2024-05-09 13:53:19 -07:00
sabaimran
7ae00832bd Rname from parameter to sender in resend call 2024-05-09 13:29:39 -07:00
sabaimran
fbd76f8ebe
Improve the UX of automations (#737)
* Improve the automations UX

- Add suggested jobs to elimiinate some of the cold start problem
- Make each of the tasks cards that are clickable/editable

* Hide suggested automations that have already been added

* Add a footer and reapply styling when a save action is taken on a card
2024-05-09 01:29:48 -07:00
sabaimran
70d0ee4310 Only remove the process lock from a process that created it 2024-05-08 10:14:52 -07:00
Desmond Deng
20303feb3a
Merge branch 'khoj-ai:master' into master 2024-05-08 13:46:34 +08:00
Desmond
150cd18bf3 Update batch-size 2024-05-08 13:44:22 +08:00
Desmond
192cd53003 Batch send of index files 2024-05-08 13:38:40 +08:00
sabaimran
a50deb2762 Add better handling for empty responses 2024-05-07 11:49:33 -07:00
sabaimran
4aed6bd274 Add an admin view for subscriptions 2024-05-07 11:48:52 -07:00
sabaimran
77626d28d1 Include stack trace when automation is not successfully craeted 2024-05-07 06:52:41 -07:00
sabaimran
0c8c565ab0 Don't include the whole stack trace for an integrity error 2024-05-07 06:48:18 -07:00
Debanjum Singh Solanky
0a1a6cd041 Get detailed user info in Obsidian from the new v1/user API
Previously we were just getting user email from the /health API
Instead store the retrieved user info in the user settings
2024-05-07 04:37:26 +08:00
Debanjum Singh Solanky
f8f9d066db Focus on input field, scroll to latest message on opening chat pane
Previously scroll and chat input focus weren't applied as view hadn't
been rendered yet
2024-05-07 04:37:26 +08:00
Debanjum Singh Solanky
9f65e8de98 Open Khoj Chat as a Pane instead of a Modal
- Allows having it open on the side as you traverse your Obsidian notes
- Allow faster time to response, having responses visible for context
- Enables ambient interactions
2024-05-07 04:37:26 +08:00
sabaimran
9ae828cf11 Use asssets.khoj.dev for loading math katex rendering 2024-05-07 01:43:46 +08:00
sabaimran
cf0b7628d0 Add the url scheme to the public share url 2024-05-06 21:37:49 +08:00
sabaimran
f6aaecb04f Fix construction method for public share conversation URL 2024-05-06 08:32:51 +05:30
sabaimran
14c9bea663
Make conversations optionally shareable (#712)
* Make conversations optionally shareable

- Shared conversations are viewable by anyone, without a login wall
- Can share a conversation from the three dot menu
- Add a new model for Public Conversation
- The rationale for a separate model is that public and private conversations have different assumptions. Separating them reduces some of the code specificity on our server-side code and allows us for easier interpretation and stricter security. Separating the data model makes it harder to accidentally view something that was meant to be private
- Add a new, read-only view for public conversations
2024-05-05 23:16:04 +05:30
Debanjum Singh Solanky
80cbaca935 Serve generated images from Khoj domain instead of directly from S3
Use CNAME to forward requests from the khoj subdomain to the
equivalent S3 bucket
2024-05-04 20:07:10 +05:30
Debanjum Singh Solanky
425496844b Rename assets URL from Khoj S3 bucket to assets.khoj.dev
Server khoj assets from khoj domain
2024-05-04 20:07:10 +05:30
sabaimran
88daa841fd Rename process lock migration and add a reverse migration step 2024-05-04 20:05:00 +05:30
sabaimran
509a8a412c Throw an error if trying to create a process lock that already exists. Names should be unique 2024-05-04 19:03:53 +05:30
sabaimran
7100614de5
Add support for rendering math equations in the web view (#733)
- Add parsing logic for LaTeX-format math equations in the web chat
- Add placeholder delimiters when converting the markdown to HTML in order to avoid removing the escaped characters
- Add the `<!DOCTYPE html>` specification to the page
2024-05-04 15:59:17 +05:30
Debanjum Singh Solanky
d9b3482b1a Show error when required fields to create automation are not set 2024-05-04 11:17:30 +05:30
Debanjum Singh Solanky
91a5643c5c Use Preview label for Automate feature. Prefix mailto: link to contact 2024-05-04 10:59:17 +05:30
Debanjum Singh Solanky
fd2328ab40 Do not hard code base url of path to automation icon in chat message 2024-05-04 10:59:07 +05:30
sabaimran
a38f3227e2 Revert domain in task task send emails 2024-05-03 15:27:27 +05:30
sabaimran
a1263951e9 Use mail to in email contact link 2024-05-03 12:16:56 +05:30
sabaimran
7c9847fe48 Increase jitter to 60 2024-05-03 11:38:22 +05:30
sabaimran
737ebfd521 Make improvements to online search prompts and use a custom domain for automations emails 2024-05-03 10:47:42 +05:30
sabaimran
42e9504ba8 Use a different function for getting last run time, avoid async/sync issues 2024-05-02 12:13:45 +05:30
sabaimran
9e8491b814 Add experimental disclaimers to the automations 2024-05-02 11:40:37 +05:30
sabaimran
c418449311 Add additional robustness in verifying job execution parameters at run time 2024-05-02 11:13:04 +05:30
sabaimran
690e9d8ed3 Collapse the reminders after they're successfully scheduled 2024-05-02 09:55:04 +05:30
sabaimran
6b648ee3ad Add experimental disclaimer in the automation page 2024-05-02 09:21:27 +05:30
sabaimran
f4fbc91515 Remove the exclamation point from the email 2024-05-01 19:01:51 +05:30
sabaimran
bddd1d0fcb Quip, smart reminders 2024-05-01 16:39:07 +05:30
sabaimran
bc8b92a77d Release Khoj version 1.12.0 2024-05-01 16:30:48 +05:30
sabaimran
b499851097 Use the cleaned query as the reference query in the email notification 2024-05-01 15:33:11 +05:30
sabaimran
f24495e0e6 Fix time zone used in query history. Closes #694 2024-05-01 15:31:48 +05:30
sabaimran
7fd57d737e Adjustments to improve overall styling of config page, email template 2024-05-01 14:19:47 +05:30
sabaimran
28578310d1 Add log line when sending a task-related email 2024-05-01 13:56:02 +05:30
sabaimran
a86f95117e Add the subject generation prompt and helper method 2024-05-01 13:55:32 +05:30
sabaimran
c30ba2e551 Set subject dynamically when creating new tasks, and make some minor improvments to the automations UI 2024-05-01 13:54:59 +05:30
sabaimran
d1b2037676 Shutdown the scheduler when the application is exiting 2024-05-01 13:53:34 +05:30
Debanjum Singh Solanky
89a8dbb81a Fix edit job API. Use user timezone, pass all reqd. params to automation
- Pass user and calling_url to the scheduled chat too when modifying
  params of automation
- Update to use user timezone even when update job via API
- Move timezone string to timezone object calculation into the
  schedule automation method
2024-05-01 10:29:49 +05:30
Debanjum Singh Solanky
19c5af3ebc Handle natural language to cron translation error on web client 2024-05-01 09:10:18 +05:30
Debanjum Singh Solanky
70ee9ddf91 Merge migrations from main with feature branch 2024-05-01 09:10:18 +05:30
Debanjum Singh Solanky
8f28f6cc1e Remove now unused location data from being passed to automation funcs 2024-05-01 08:48:16 +05:30
Debanjum Singh Solanky
815966cb25 Unify, modularize DB adapters to get automation metadata by user further 2024-05-01 08:47:50 +05:30
Debanjum Singh Solanky
21bdf45d6f Add link to Automate page in nav pane of the web app 2024-05-01 08:47:50 +05:30
Debanjum Singh Solanky
bd5008136a Move automations into independent page. Allow direct automation
- Previously it was a section in the settings page. Move it to
  independent, top-level page to improve visibility of feature

- Calculate crontime from natural language on web client before
  sending it to to server for saving new/updated schedule to disk.
  - Avoids round-trip of call to chat model

- Convert POST /api/automation API endpoint into a direct request for
  automation with query_to_run, subject and schedule provided via the
  automation page. This allows more granular control to create automation
  - Make the POST automations endpoint more robust; runs validation
    checks, normalizes parameters
2024-05-01 08:47:48 +05:30
Debanjum Singh Solanky
cbc8a02179 Make, use func for constructing the automation created response
- Dedupe logic across http, ws chat API endpoints
- Reduces size of already too long http, ws chat API endpoint funcs
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
c52ed333fa Make content, cards on config pages occupy the whole middle column
- Make the config page content use  the same top level 3-column layout
  as the khoj-header-wrapper
  This ensures the content is aligned with heading pane width
- Let cards and other settings sections scale to the width of their
  grid element. This utilizes more of the screen space and does it
  consistently across the different settings pages
2024-05-01 08:30:10 +05:30
sabaimran
ad4145e48c Fix unique has for job id 2024-05-01 08:30:10 +05:30
sabaimran
311d58e1ed Ensure the automated_task command is removed from the prepended query 2024-05-01 08:30:10 +05:30
sabaimran
eb65532386 Use Django ap scheduler in place of the sqlalchemy one 2024-05-01 08:30:10 +05:30
sabaimran
06213ea814 Fix token retrieval when executing the job and name async job approriately 2024-05-01 08:30:10 +05:30
sabaimran
ca8a7d8368 Revert sync -> aync in send welcome email method 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
6936875a82 Use DB adapter to unify logic to get, delete automation by auth user
To use place with logic to get, view, delete (and edit soon) automations
by (authenticated) user, instead of scattered across code
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
1238cadd31 Allow editting query-to-run from the automation config section 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
cb2b1dccc5 Add icon for Automation feature. Replace old icons for delete, new 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
23f2057868 Allow creating automations from automation settings section in web ui
- Create new POST API endpoint to create automations
- Use it in the settings page on the web interface to create
  new automations

This simplified managing automations from the setting page by allowing
both delete and create from the same page
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
2f9241b5a3 Rename scheduled task to automations across code and UX
- Fix query, subject parameters passed to email template
- Show 12 hour scheduled time in automation created chat message
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
230d160602 Improve rendering task scheduled settings view and message
- Render crontime string in natural language in message & settings UI
- Show more fields in tasks web config UI
- Add link to the tasks settings page in task scheduled chat response
- Improve task variables names
  Rename executing_query to query_to_run. scheduling_query to
  scheduling_request
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
d341b1efe8 Store, retrieve task metadata from the job name field 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
ae10ff4a5f Create create_scheduled_task func to dedupe logic across ws, http APIs
Previously, both the websocket and http endpoint were implementing
the same logic. This was becoming too unwieldy
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
8dfa0bf047 Simplify task scheduler prompt. No timezone conversion. Infer subject
- Make timezone aware scheduling programmatic, instead of asking the
  chat model to do the conversion. This removes the need for
  scratchpad and may let smaller models handle the task as well
- Make chat model infer subject for email. This should make the
  notification email more readable
- Improve email by using subject in email subject, task heading. Move
  query to email final paragraph, which is where task metadata  should
  go
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
2c563ad280 Use hash of query in process lock id to standardize id format
- Using inferred_query directly was brittle (like previous job id)
- And process lock id had a limited size, so wouldn't work for larger
  inferred query strings
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
3ce06a938c Render scheduled task response as html to improve readability in email 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
c17dbbeb92 Render next run time in user timezone in config, chat UIs
- Pass timezone string from ipapi to khoj via clients
  - Pass this data from web, desktop and obsidian clients to server
- Use user tz to render next run time of scheduled task in user tz
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
6736551ba3 Improve scheduled task text rendered in UI 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
0e01362469 Merge DB migrations from master with those from scheduled task feature 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
a5ed4f2af2 Send email to share results of scheduled task 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
69775b6d6e Add /task command. Use it to disable scheduling tasks from tasks
This takes the load of the task scheduling chat actor / prompt from
having to artifically differentiate query to create scheduled task
from a scheduled task run.
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
22289a0002 Improve task scheduling by using json mode and agent scratchpad
- The task scheduling actor was having trouble calculating the
  timezone. Giving the actor a scratchpad to improve correctness by
  thinking step by step
- Add more examples to reduce chances of the inferred query looping to
  create another reminder instead of running the query and sharing
  results with user
- Improve task scheduling chat actor test with more tests and
  by ensuring unexpected words not present in response
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
7f5981594c Only notify when scheduled task results satisfy user's requirements
There's a difference between running a scheduled task and notifying
the user about the results of running the scheduled task.

Decide to notify the user only when the results of running the
scheduled task satisfy the user's requirements.

Use sync version of send_message_to_model_wrapper for scheduled tasks
2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
7e084ef1e0 Improve job id. Fix refreshing list of jobs on delete from config page 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
a1e5195c8b Save separate user message time from Khoj response time in chat logs
Previously user message time was being stored the same as Khoj
response time in conversation logs.
2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
5133b6e73b Minor improvements to styling the config page 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
648f1a5c71 Suffix chat response element vars with "El" in chat.html of web, desktop apps 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
98d0ffecf1 Add section in settings page to view, delete your scheduled tasks 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
423d61796d Add API endpoints to get and delete user scheduled tasks 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
af0972c539 Make scheduled jobs persistent and work in multiple worker setups
- Store scheduled job state in Postgres so job schedules persist
  across app restarts
- Use Process Locks to only allow single worker to process a given job
  type. This prevents duplicating job runs across all workers
2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
fcf878e1f3 Add new operation Scheduled Job to Operation enum of ProcessLock 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
c11742f443 Add chat actor to schedule run query for user at specified times
- Detect when user intends to schedule a task, aka reminder
  Add new output mode: reminder. Add example of selecting the reminder
  output mode
- Extract schedule time (as cron timestring) and inferred query to run
  from user message
- Use APScheduler to call chat with inferred query at scheduled time
- Handle reminder scheduling from both websocket and http chat requests

- Support constructing scheduled task using chat history as context
  Pass chat history to scheduled query generator for improved context
  for scheduled task generation
2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
9e068fad4f Handle null ref, when refresh conversation from db in websocket chat 2024-04-30 14:19:07 +05:30
sabaimran
37879a7850 Release Khoj version 1.11.2 2024-04-30 13:31:06 +05:30
sabaimran
93b41170d1 Refresh the conversation log from the db before addressing the next query 2024-04-30 13:27:51 +05:30
Debanjum Singh Solanky
f1545d2b2f Add, fix help link, improve title style in web ui config pages
- Align title text with icon better in all config cards
- Fix help link to github setup docs
- Fix help link to notion setup docs
2024-04-30 05:50:08 +05:30
Debanjum Singh Solanky
e6da0f9a8c Fix response type of delete client tokens API endpoint
Previously the make delete API response failed, after deleting token.
Required a page refresh to see that the API token was actually gone.

This was happening because the response type of the delete token API
endpoint isn't a string, so it failed FastAPI response validation
checks.
2024-04-30 02:46:52 +05:30
sabaimran
0f4c3518d3 Allow session cookies to be stored with a lax policy for some localhost scenarios 2024-04-29 15:48:45 +05:30
sabaimran
5beedc9734 Use Secure proxy ssl header only if no https 2024-04-29 15:33:21 +05:30
sabaimran
12258f02d7 Release Khoj version 1.11.1 2024-04-27 18:42:24 +05:30
sabaimran
2047b0c973
Support customization of the OpenAI base url in admin settings (#725)
- Allow self-hosted users to customize their open ai base url. This allows you to easily use a proxy service and extend support for other models.
- This also includes a migration that associates any existing openai chat model configuration with an openai processor configuration
- Make changing model a paid/subscriber feature
- Removes usage of langchain's OpenAI wrapper for better control over parsing input/output
2024-04-27 18:24:35 +05:30
sabaimran
49834e3b00 Add a hero image for the og:image meta tag 2024-04-27 17:07:21 +05:30
sabaimran
138f12f957 Fix indentation and revert first run message link styling to all links 2024-04-27 09:56:58 +05:30
Debanjum Singh Solanky
4395ed8065 Improve extract_questions func. Set message role to user, not assistant
Previous behavior of passing message with role = "assistant was
reducing instruction following quality of the model
2024-04-26 11:55:22 +05:30
Debanjum Singh Solanky
346499f12c Fix, improve args being passed to chat_completion args
- Allow passing completion args through completion_with_backoff
- Pass model_kwargs in a separate arg to simplify this
- Pass model in `model_name' kwarg from the send_message_to_model func
  `model_name' kwarg is used by langchain, not `model' kwarg
2024-04-26 11:55:22 +05:30
sabaimran
d8f2eac6e0 Release Khoj version 1.11.0 2024-04-25 17:24:59 +05:30
Debanjum Singh Solanky
1842017393 Skip trying to index deleted files, folders from Desktop app
Previously app would crash on startup if desktop app was told to
index a file that had been deleted afterwards
2024-04-25 15:23:05 +05:30
Debanjum
17a06f152c
Support Llama 3 and Improve Offline Chat Actors (#724)
- Add support for Llama 3 in Khoj offline mode
- Make chat actors generate valid json with more local models
- Fix offline chat actor tests
2024-04-25 14:00:56 +05:30
Debanjum
220e5516ab
Make Search Models More Configurable. Upgrade Default Cross-Encoder (#722)
- Upgrade default cross-encoder to mixedbread ai's mxbai-rerank-xsmall
- Support more embedding models by making query, docs encoding configurable
2024-04-25 13:55:49 +05:30
Debanjum Singh Solanky
cf08eaf786 Add comments explaining each field in the search model config in DB 2024-04-25 13:54:13 +05:30
Debanjum
4ee5ac7c20
Fix Chat UI and Indexing on Desktop App (#723)
- Make valid file extension checking case insensitive on Desktop app
- Skip indexing non-existent folders on Desktop app
- Pass auth headers to fix lazy load of chat messages on Desktop app
- Set chat-message height to height of content in web, desktop
2024-04-24 18:49:03 +05:30
Debanjum Singh Solanky
799efb5974 Create DB migration to add new fields and change default cross-encoder 2024-04-24 09:50:34 +05:30
Debanjum Singh Solanky
ec41482324 Upgrade default cross-encoder to mixedbread ai's mxbai-rerank-xsmall
Previous cross-encoder model was a few years old, newer models should
have improved in quality. Model size increases by 50% compared to
previous for better performance, at least on benchmarks
2024-04-24 09:50:09 +05:30
Debanjum Singh Solanky
7eaf9367fe Support more embedding models by making query, docs encoding configurable
Most newer, better embeddings models add a query, docs prefix when
encoding. Previously Khoj admins couldn't configure these, so it
wasn't possible to use these newer models.

This change allows configuring the kwargs passed to the query, docs
encoders by updating the search config in the database.
2024-04-24 09:49:17 +05:30
Debanjum Singh Solanky
4f7237b158 Make chat actors generate valid json with more local models
Improve tool, online search, webpage links, docs search chat actor
prompts. Ensure works with hermes-2-pro and llama-3.

Be more specific about generating JSON and not saying anything else.
2024-04-24 09:40:00 +05:30
Debanjum Singh Solanky
a2e4e4bede Add support for Llama 3 in Khoj offline mode
- Improve extract question prompts to explicitly request JSON list
- Use llama-3 chat format if HF repo_id mentions llama-3. The
  llama-cpp-python logic for detecting when to use llama-3 chat format
  isn't robust enough currently
2024-04-24 09:40:00 +05:30
Debanjum Singh Solanky
8e77b3dc82 Fix infer_max_tokens func when configured_max_tokens is set to None 2024-04-24 09:36:29 +05:30
Debanjum Singh Solanky
8196ab62f9 Make valid file extension checking case insensitive on Desktop app 2024-04-24 09:35:20 +05:30
Debanjum Singh Solanky
5def14e3bb Skip indexing non-existent folders on Desktop app 2024-04-24 09:35:20 +05:30
Debanjum Singh Solanky
cd05f262a6 Pass auth headers to fix lazy load of chat messages on Desktop app 2024-04-24 09:35:20 +05:30
Debanjum Singh Solanky
4d5d3e6433 Set chat-message height to height of content in web, desktop
In some cases, especially with image generation requests, this was
causing the chat messages to overlap in the chat UI
2024-04-24 09:35:20 +05:30
sabaimran
60658a8037 Get rid of enable flag for the offline chat processor config
- Default, assume that offline chat is enabled if there is an offline chat model option configured
2024-04-23 23:08:29 +05:30
sabaimran
ac474fce38 Ensure that the tokenizer and max prompt size are used the wrapper method 2024-04-23 21:22:23 +05:30
Olatoyan George
ad59180fb8
Added indication in the desktop UI for back-end connectivity (#711)
* Changed the styling of the link that takes a user to the settings page into a button
* added an indicator that shows if a user is connected to the server or not
* made a class name more descriptive and also made the text in first run message more intuitive
* changed the command to install dependencies in the README.md
* changed the class name of the first run message text to be more descriptive
* added icons in the desktop UI that shows if a file is synced successfully or not
* made the link class name in the homepage more descriptive
* fixed the hover issue on status box in the chat header pane
* fixed hovering issue on status box on macOS
2024-04-23 16:43:48 +05:30
Debanjum
419b044ac5
Use set, inferred max token limits wherever chat models are used (#713)
- User configured max tokens limits weren't being passed to
  `send_message_to_model_wrapper'
- One of the load offline model code paths wasn't reachable. Remove it
  to simplify code
- When max prompt size isn't set infer max tokens based on free VRAM
  on machine
- Use min of app configured max tokens, vram based max tokens and
  model context window
2024-04-23 16:42:35 +05:30
AjaySDwivedi1
abf6f963ea
Replaced reinitialize and save all button to a sync button in config.… (#701)
Replaced reinitialize and save all button to a sync button in config
2024-04-23 16:42:11 +05:30
Debanjum Singh Solanky
c39c4e4ec4 Improve prompt for online search query generation chat actor
- Allow searching github, pypi for information about Khoj
- Enable creating multiple search queries by rewording prompt
2024-04-22 01:32:11 +05:30
Debanjum Singh Solanky
175169c156 Use set, inferred max token limits wherever chat models are used
- User configured max tokens limits weren't being passed to
  `send_message_to_model_wrapper'
- One of the load offline model code paths wasn't reachable. Remove it
  to simplify code
- When max prompt size isn't set infer max tokens based on free VRAM
  on machine
- Use min of app configured max tokens, vram based max tokens and
  model context window
2024-04-20 11:23:28 +05:30
Debanjum Singh Solanky
002cd14a65 Only let agent use online search tool if connected to it 2024-04-20 11:19:48 +05:30
Debanjum Singh Solanky
75c9ebbc54 Only show uvicorn debug logs at higher verbosity levels
Don't automatically show the uvicorn logs when in_debug_mode, only
show on at least verbosity = 2, i.e when start khoj with -vv flag
2024-04-20 11:18:01 +05:30
sabaimran
d11354f9c8 Remove additional references to image content config 2024-04-17 13:00:50 +05:30
sabaimran
105dbf49e4 Fix max_duration_in_seconds for the update_embeddings job 2024-04-17 13:00:18 +05:30
Debanjum Singh Solanky
8e0bae894d Extract run with process lock logic into func. Use for content reindexing 2024-04-17 12:31:19 +05:30
Debanjum Singh Solanky
e9f608174b Fix access to Khoj admin panel from non HTTPS custom domains
To access the Khoj admin panel from a non HTTPS custom domain the
`KHOJ_NO_SSL' and `KHOJ_DOMAIN' env vars need to be explictly set.

See the updated setup docs for details.

Resolves #662
2024-04-17 03:20:05 +05:30
sabaimran
b0059654c9 Do not create an import error if the resend module is not available 2024-04-17 01:00:22 +05:30
sabaimran
f04ead7c37 Remove seting up log line for configuring image search 2024-04-17 00:45:39 +05:30
sabaimran
0208688801 Increase factor for n_ctx reduciton to 2e6 2024-04-17 00:41:36 +05:30
Debanjum Singh Solanky
1f2ffce85b Copy chat message with it's markdown formatting in Web, Desktop apps 2024-04-16 22:10:34 +05:30
sabaimran
91c8b137f1
Add a database lock for jobs that shouldn't be run by multiple workers (#706)
* Add a database lock for jobs that shouldn't be run by multiple workers

* Import relevant functions from utils.helpers
2024-04-16 21:29:27 +05:30
sabaimran
adb2e8cc5f Check if n is populated before making a comparison 2024-04-16 02:05:58 +05:30
Debanjum Singh Solanky
6707ccc463 Check before updating "chat" key in meta_log in chat history API endpoint 2024-04-15 21:06:47 +05:30
Debanjum Singh Solanky
4e7812fe55 Use Django management cmd to update inline images in DB to/from WebP/PNG
This provides Khoj server admins more control on migrating their S3
images to WebP format from PNG
2024-04-15 20:19:49 +05:30
Debanjum Singh Solanky
7fab8d6586 Only use chat messages count in history API endpoint when set by client 2024-04-15 19:12:57 +05:30
Debanjum
6b3ef61dd2
Improve Chat Page Load Perf, Offline Chat Perf and Miscellaneous Fixes (#703)
### Store Generated Images as WebP 
- 78bac4ae Add migration script to convert PNG to WebP references in database
- c6e84436 Update clients to support rendering webp images inline
- d21f22ff Store Khoj generated images as webp instead of png for faster loading

### Lazy Fetch Chat Messages to Improve Time, Data to First Render
This is especially helpful for long conversations with lots of images
- 128829c4 Render latest msgs on chat session load. Fetch, render rest as they near viewport
- 9e558577 Support getting latest N chat messages via chat history API

### Intelligently set Context Window of Offline Chat to Improve Performance
- 4977b551 Use offline chat prompt config to set context window of loaded chat model

### Fixes
- 148923c1 Fix to raise error on hitting rate limit during Github indexing
- b8bc6bee Always remove loading animation on Desktop app if can't login to server
- 38250705 Fix `get_user_photo` to only return photo, not user name from DB

### Miscellaneous Improvements
- 689202e0 Update recommended CMAKE flag to enable using CUDA on linux in Docs
- b820daf3 Makes logs less noisy
2024-04-15 18:34:29 +05:30
Debanjum Singh Solanky
a352940dfd Use Django management command to update images URL in DB to WebP
This provides Khoj server admins more control on migrating their S3
images to WebP format from PNG
2024-04-15 17:53:41 +05:30
Debanjum Singh Solanky
7d8e8eb0cf Use Enum to type text-to-image intent of Khoj chat response 2024-04-15 17:53:40 +05:30
Debanjum Singh Solanky
128829c477 Show latest msgs on chat session load. Fetch rest as they near viewport
- Reduces time to first render when loading long chat sessions
- Limits size of first page load, when loading long chat sessions

These performance improvements are maximally felt for large chat
sessions with lots of images generated by Khoj

Updated web and desktop app to support these changes for now
2024-04-15 16:10:56 +05:30
Debanjum Singh Solanky
9e5585776c Support getting latest N chat messages via chat history API
Get latest N if N > 0, else return all messages except latest N from
the conversation
2024-04-15 15:32:32 +05:30
Debanjum Singh Solanky
e5ff85f6fb Start fetching khoj css before icons to reduce time with no styling
This should reduce frequency of page load jitter when icons are loaded
before style is applied
2024-04-15 15:32:32 +05:30
Debanjum Singh Solanky
d5de59d411 Do not assume results key present in notion content when indexing 2024-04-15 08:02:20 +05:30
Debanjum Singh Solanky
4977b55106 Use offline chat prompt config to set context window of loaded chat model
Previously you couldn't configure the n_ctx of the loaded offline chat
model. This made it hard to use good offline chat model (which these
days also have larger context) on machines with lower VRAM
2024-04-14 02:35:36 +05:30
Debanjum Singh Solanky
148923c13a Fix to raise error on hitting rate limit during Github indexing 2024-04-13 22:09:13 +05:30
sabaimran
f24d71c71c
Improve the agents UX (#702)
- Make the chat buttons look more clickable
- Show agent name in new conversation message
- Add an icon to the CTA to send agent a message
2024-04-13 20:11:37 +05:30
Debanjum Singh Solanky
78bac4ae05 Add migration script to convert PNG to WebP references in database 2024-04-13 19:06:28 +05:30
Debanjum Singh Solanky
c6e8443631 Update clients to support rendering webp images inline
This is for self-hosted scenarios where AWS S3 uploads is not enabled
2024-04-13 13:11:18 +05:30
Debanjum Singh Solanky
d21f22ffa1 Store Khoj generated images as webp instead of png for faster loading 2024-04-13 13:03:32 +05:30
Debanjum Singh Solanky
b820daf38f Makes logs less noisy
- Show telemetry enabled/disabled state on init, not every 2 minutes
- Convert no docs synced logs to debug level instead of warning
  Having synced docs isn't as important to use Khoj now, unlike before
2024-04-13 11:22:58 +05:30
Debanjum Singh Solanky
b8bc6bee83 Always remove loading animation on Desktop app if can't login to server 2024-04-13 11:02:44 +05:30
Debanjum Singh Solanky
382507051f Fix get_user_photo to only return photo, not user name from DB 2024-04-13 11:02:30 +05:30
sabaimran
f06ec485cb Fix redirect url process for login flow, existing user 2024-04-12 17:10:05 +05:30
sabaimran
b86e68a29d Make it easier to view agents in the admin page 2024-04-12 13:02:22 +05:30
sabaimran
1377a44a1a Suppress debug logs from uvicorn.error to avoid clutter from websockets
- If application is not in DEBUG_MODE
2024-04-12 12:12:16 +05:30
Debanjum Singh Solanky
89b8ec3546 Release Khoj version 1.10.2 2024-04-12 11:53:32 +05:30
Debanjum Singh Solanky
50b4788a91 Remove chat loading animation in login required state on Desktop app 2024-04-12 11:50:54 +05:30
Debanjum Singh Solanky
b3f4794d91 Remove the unnecessary async/await func chains on Desktop app 2024-04-12 11:49:25 +05:30
Debanjum Singh Solanky
1e30a072d4 Just use file ext to identify indexable files to fix Desktop app install
- Magika on Desktop app was too bloated (100Mb to 250Mb) and broke
  install for some reason. Not sure why it was causing the app install
  to fail but do not have time to currently investigate

- Just use file extensions whitelist it's good enough for now. Let
  server handle the deeper identification of file type
2024-04-12 11:16:07 +05:30
Debanjum Singh Solanky
5c7797dbca Only check content type if file extension cannot identify text file 2024-04-12 03:40:42 +05:30
Debanjum Singh Solanky
7d2ef728e6 Fix identifying pdf files on server
Introduced bug in previous commit that would stop indexing PDF files
as trying to check content_group instead of mime_type is application/pdf
2024-04-12 03:07:46 +05:30
Debanjum Singh Solanky
07f8fb5c5b Release Khoj version 1.10.1 2024-04-12 02:18:07 +05:30
Debanjum Singh Solanky
a7d9102c33 Make identifying text, code files with Magika more robust on server
Use identified content group rather than mime_type to find text files.
2024-04-12 02:12:26 +05:30
Debanjum Singh Solanky
60337086f9 Release Khoj version 1.10.0 2024-04-12 01:01:02 +05:30
Debanjum Singh Solanky
34c3f70203 Index only files with valid text extension in folders synced by Desktop app
This maintains consistent set of indexable files from Desktop app,
whether indexing via file or folder filters
2024-04-12 00:59:54 +05:30
Debanjum
9a48f72041
Index more text file types from Desktop, Github (#692)
### Index more text file types 
- Index all text, code files in Github repos. Not just md, org files
- Send more text file types from Desktop app and improve indexing them
- Identify file type by content & allow server to index all text files

### Deprecate Github Indexing Features
- Stop indexing commits, issues and issue comments in a Github repo
- Skip indexing Github repo on hitting Github API rate limit

### Fixes and Improvements
- **Fix indexing files in sub-folders from Desktop app**
- Standardize structure of text to entries to match other entry processors
2024-04-12 00:08:29 +05:30
Debanjum Singh Solanky
0819b83d0b Fix constructing status update strings for intermediate chat steps 2024-04-11 20:31:32 +05:30
Debanjum Singh Solanky
d15b9bc272 Tell doc search actor to not generate online queries for doc search
This can pick up irrelevant details from notes
2024-04-11 19:49:41 +05:30
Debanjum Singh Solanky
15a78b19ad Improve Inferred Document Search Query Extraction from GPT
Using stop_words = "\n" was preventing JSON responses with newlines in
them
2024-04-11 19:24:04 +05:30
Debanjum Singh Solanky
653681967e Show inferred document search queries in intermediate chat step on Web app 2024-04-11 19:24:04 +05:30
Debanjum Singh Solanky
997741119a Show better intermediate steps when responding to chat via web socket
- Show internet search, webpage read, image query, image generation steps
- Standardize, improve rendering of the intermediate steps on the web app

Benefits:
1. Improved transparency, allow users to see what Khoj is doing behind
   the scenes and modify their query patterns to improve response quality
2. Reduced websocket connection keep alive timeouts for long running steps
2024-04-11 18:04:40 +05:30
sabaimran
fae7900f19 Remove more 2024-04-11 00:27:44 +05:30
sabaimran
5d1dd3e2b7 If resend not enabled, don't send the welcome email 2024-04-10 23:52:42 +05:30
sabaimran
d2f9c43c8e Use datetime.timezone.utc instead of datetime.utc 2024-04-10 23:07:43 +05:30
Debanjum Singh Solanky
f2dc9709b7 Use Magika to more robustly identify text files to send for indexing
- `file-type' doesn't handle mis-labelled files or files without
   extensions well

- Only show supported file types in file selector dialog on Desktop app
  Use Magika to get list of text file extensions. Combine with other
  supported extensions to get complete list of supported file extensions.
  Use it to limit selectable files in the File Open dialog.

  Note: Folder selector will index text files with no extensions as well
2024-04-10 22:44:24 +05:30
sabaimran
3fe94a67b0
Send welcome emails when a new user signs up (#691)
* Don't trigger any re-indexing on server initailization

* Integrate Resend to send welcome emails when a new user signs up

- Only send if this is the first time they've signed in
- Configure welcome email with basic styling, as more complex designs don't work and style tag did not work
2024-04-10 19:57:33 +05:30
Debanjum
6d153022f6
Improve nav pane, chat session UI on Desktop, Web app (#693)
### Enable copying chat messages. Improve copy button behavior and styling
  - Add button to copy chat messages on Desktop, Web apps
  - Improve copy button's icon, hover color & click animation in Desktop, Web apps

### Improve Navigation, Chat Session Panes on Desktop, Web apps
  - Dynamically generate navigation menu based on user info from server
  - Create API endpoint to get authenticated user information
  - Collapse navigation tabs into icons on mobile. Add spacing to them
  - Add Chat navigation tab back to top pane on Web app
  - Use proper icons for Search, Chat and Agents tab on navigation pane
  
### Miscellaneous Improvements
  - Make current chat expand to full width when session panel collapsed on Desktop App
  - Add chat session loading spinner to Desktop App (same as Web app)
   
### Fixes 
  - Show title bar in Khoj desktop app on Windows to simplify close, minimize etc.
  - Only render first run setup message once if error or server not running
  - Fix showing Search navigation tab from Agent pages on web client
2024-04-10 19:54:12 +05:30
Debanjum Singh Solanky
48d249db9e Center the nav item text and user profile initial icons 2024-04-10 19:38:43 +05:30
Debanjum Singh Solanky
60f6a1c6f1 Use svg icons in nav pane to standardize styling on Web, Desktop apps
Emojis varied based on device. svg icons standardize icon styles of
the web, desktop apps
2024-04-10 19:38:43 +05:30
Debanjum Singh Solanky
cccea484e4 Pass username, location context in system prompt instead of chat message
The username and location in system prompt should disambiguate user
context from user's actual message for the chat model.

It doesn't need to be told to not mention the context or acknowledge
the context instructions in it's response, as it understands that this
information is just context and not part of the user's actual message.
2024-04-10 15:05:33 +05:30
Debanjum Singh Solanky
804c04f7b9 Do not render copy message button on every Khoj thinking step
Only render copy chat message button once, after message text is rendered
2024-04-10 14:48:36 +05:30
sabaimran
a4afada746 Remove client-side timeouts for the khoj socket 2024-04-10 13:35:25 +05:30
Debanjum Singh Solanky
cadeaac769 Align conversation sessions side panel on Desktop app with Web app
- Move new conversation button to right of "Conversation" title
- Reduce size of chat message loading ellipsis animation
- Add loading animation for chat session
2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
1c3d129e08 Add button to copy chat messages on Desktop client 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
0a5a91619e Improve copy button's icon, hover color & click animation in Desktop UI 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
184873213c Add button to copy chat messages on Web client 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
f56522cb8e Improve copy button's icon, hover color & click animation in Web UI 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
8ff3890ba8 Dynamically generate navigation menu based on user info from server 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
94c69eb8e3 Create API endpoint to get authenticated user information
This help clients render UI with user information
2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
377e979800 Make current chat expand to full width when session panel collapsed
This behavior also matches web client behavior on chat session panel
collapse
2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
913dcdfbcd Only render first run setup message once if error or server not running 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
3b630841bd s/aget_all_filenames_by_source/get_all_filenames_by_source as sync func 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
e45edbb992 Collapse navigation tabs into icons on mobile. Add spacing to them 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
93edd5427f Add Chat navigation tab back to top pane on web client
Reduces user confusion on how to go to chat pane
Add emoji's for each tab to provide cleaner, iconified division between
the nav options
2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
8159d1ab25 Fix showing Search navigation tab from Agent pages on web client
The `has_documents' flag wasn't being passed. So the search tab
always showing up as empty instead of being dynamically enabled if
documents had been indexed.
2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
76cb543347 Show title bar in Khoj desktop app on Windows 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
f040418cf1 Fix indexing files in sub-folders on the Desktop app
- `fs.readdir' func in node version 18.18.2 has buggy `recursive' option
  See nodejs/node#48640, effect-ts/effect#1801 for details

- We were recursing down a folder in two ways on the Desktop app.
  Remove `recursive: True' option to the `fs.readdirSync' method call
  to recurse down via app code only
2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
a8dec1c9d5 Index all text, code files in Github repos. Not just md, org files 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
8291b898ca Standardize structure of text to entries to match other entry processors
Add process_single_plaintext_file func etc with similar signatures as
org_to_entries and markdown_to_entries processors

The standardization makes modifications, abstractions easier to create
2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
079f409238 Skip indexing Github repo on hitting Github API rate limit
Sleep until rate limit passed is too expensive, as it keeps a
app worker occupied.

Ideally we should schedule job to contine after rate limit wait time
has passed. But this can only be added once we support jobs scheduling.
2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
d5c9b5cb32 Stop indexing commits, issues and issue comments in Github indexer
Normal indexing quickly Github hits rate limits. Purpose of exposing
Github indexer is for indexing content like notes, code and other
knowledge base in a repo.

The current indexer doesn't scale to index metadata given Github's
rate limits, so remove it instead of giving a degraded experience of
partially indexed repos
2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
7ff1bd9f8b Send more text file types from Desktop app and improve indexing them
- Allow syncing more file types from desktop app to index on server
  - Use `file-type' package to identify valid text file types on Desktop app

- Split plaintext entries into smaller logical units than a whole file
  Since the text splitting upgrades in #645, compiled chunks have more
  logical splits like paragraph, sentence.
  Show those (potentially) smaller snippets to the user as references

- Tangential Fix:
  Initialize unbound currentTime variable for error log timestamp
2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
89915dcb4c Identify file type by content & allow server to index all text files
- Use Magika's AI for a tiny, portable and better file type
  identification system
- Existing file type identification tools like `file' and `magic'
  require system level packages, that may not be installed by default
  on all operating systems (e.g `file' command on Windows)
2024-04-09 20:19:39 +05:30
sabaimran
312528d471 Fix typo in SECURE_PROXY_SSL_HEADER settings 2024-04-09 12:33:21 +05:30
sabaimran
e56c5e67dd Revert SSL Redirect setting as it prevents the admin page from loading 2024-04-09 12:24:48 +05:30
sabaimran
1770bb174b Add UUID to the KhojUser search fields and inc frequency of telemetry job to 2 mins 2024-04-09 11:51:51 +05:30
sabaimran
ab51ae9091 Use SECURE_SSL_REDIRECT to ensure requests are routed to https always 2024-04-09 10:18:12 +05:30
sabaimran
1c229dad91 Set daily limit for unsubsribed users to 5 in websocket API 2024-04-08 21:16:48 +05:30
sabaimran
27815d982c Redirect user to the login page when either of the csrf token inputs is missing 2024-04-08 20:22:17 +05:30
sabaimran
d257629f81 Handle case when properties field isn't present in the page 2024-04-08 16:15:47 +05:30
sabaimran
089e0d028b Add a more gracefull error message when the rate limit is exceeded 2024-04-08 15:20:54 +05:30
Debanjum
11ce3e2268
Update Text Chunking Strategy to Improve Search Context (#645)
## Major
- Parse markdown, org parent entries as single entry if fit within max tokens
- Parse a file as single entry if it fits with max token limits
- Add parent heading ancestry to extracted markdown entries for context
- Chunk text in preference order of para, sentence, word, character

## Minor
- Create wrapper function to get entries from org, md, pdf & text files
- Remove unused Entry to Jsonl converter from text to entry class, tests
- Dedupe code by using single func to process an org file into entries

Resolves #620
2024-04-08 13:56:38 +05:30
Debanjum Singh Solanky
67b1178aec Remove debug logs generated while compiling org-mode entries 2024-04-08 13:01:24 +05:30
sabaimran
731ad03348 Skip indexing commits that are missing properties 2024-04-07 15:19:07 +05:30
sabaimran
376eaf64cd Check if results are present in the pages or db response in Notion 2024-04-07 15:19:07 +05:30
Debanjum Singh Solanky
8222615280 Do not add original user message to knowledge search queries for offline chat
It's not required anymore. The extracted questions by the offline chat
model being used should be good enough.
2024-04-07 11:29:35 +05:30
sabaimran
351fb31a34 Add webpage search to socket codepath, add a feature page for online search 2024-04-07 09:23:29 +05:30
Debanjum Singh Solanky
4be4c53222 Release Khoj version 1.9.0 2024-04-05 17:13:58 +05:30
sabaimran
2aedd3c819 Increase freq. of telemetry upload to every 5 minutes 2024-04-05 14:13:47 +05:30
sabaimran
3b1234d084 Await the calls to the db in the notion.py file 2024-04-05 13:58:14 +05:30
sabaimran
00a67e9524 Add additional log lines when configuring the Notion settings for a user in the callback 2024-04-05 13:19:24 +05:30
sabaimran
d23f7da8e3 Handle the case where a previous serach model isn't set when updating the model 2024-04-05 13:18:51 +05:30
sabaimran
f57f9f672d
Address Notion, Image tech debt in indexing code path (#687)
* Add support for using OAuth2.0 in the Notion integration
* Add notion to the admin page
* Remove unnecessary content_index and image search/setup references
* Trigger background job to start indexing Notion after user configures it
* Add a log line when a new Notion integration is setup
* Fix references to the configure_content methods
2024-04-05 12:10:03 +05:30
sabaimran
a60321b68e Push khoj to include inline references when possible 2024-04-04 10:31:13 +05:30
sabaimran
5bdcb4e69c Wait for location data to be returned before setting up the socket connection 2024-04-04 10:31:13 +05:30
Debanjum Singh Solanky
00f599ea78 Fix passing flags to re.split to break org, md content by heading level
`re.MULTILINE' should be passed to the `flags' argument, not the
`max_splits' argument of the `re.split' func

This was messing up the indexing by only allowing a maximum of
re.MULTILINE splits. Fixing this improves the search quality to
previous state
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
32ac0622ff Extract dates from compiled text entries 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
29c1c18042 Increase search distance to get relevant content for chat post indexer update
More content indexed per entry would result in an overall scores
lowering effect. Increase default search distance threshold to counter that

- Details
  - Fix expected results post indexing updates
  - Fix search with max distance post indexing updates

- Minor
  - Remove openai chat actor test for after: operator as it's not expected anymore
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
ad4fa4b2f4 Fix adding file path instead of stem to markdown entries 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
44b3247869 Update logical splitting of org-mode text into entries
- Major
  - Do not split org file, entry if it fits within the max token limits
    - Recurse down org file entries, one heading level at a time until
      reach leaf node or the current parent tree fits context window
    - Update `process_single_org_file' func logic to do this recursion

  - Convert extracted org nodes with children into entries
    - Previously org node to entry code just had to handle leaf entries
    - Now it recieve list of org node trees
    - Only add ancestor path to root org-node of each tree
    - Indent each entry trees headings by +1 level from base level (=2)

- Minor
  - Stop timing org-node parsing vs org-node to entry conversion
    Just time the wrapping function for org-mode entry extraction
    This standardizes what is being timed across at md, org etc.
  - Move try/catch to `extract_org_nodes' from `parse_single_org_file'
    func to standardize this also across md, org
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
eaa27ca841 Only add spaces after heading if any tags in orgnode raw entry repr 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
2ea8a832a0 Log error when fail to index md file. Fix, improve typing in md_to_entries 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
44eab74888 Dedupe code by using single func to process an org file into entries
Add type hints to orgnode and org-to-entries packages
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
db2581459f Parse markdown parent entries as single entry if fit within max tokens
These changes improve context available to the search model.
Specifically this should improve entry context from short knowledge trees,
that is knowledge bases with sparse, short heading/entry trees

Previously we'd always split markdown files by headings, even if a
parent entry was small enough to fit entirely within the max token
limits of the search model. This used to reduce the context available
to the search model to select appropriate entries for a query,
especially from short entry trees

Revert back to using regex to parse through markdown file instead of
using MarkdownHeaderTextSplitter. It was easier to implement the
logical split using regexes rather than bend MarkdowHeaderTextSplitter
to implement it.
- DFS traverse the markdown knowledge tree, prefix ancestry to each entry
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
982ac1859c Parse markdown file as single entry if it fits with max token limits
These changes improve entry context available to the search model
Specifically this should improve entry context from short knowledge trees,
that is knowledge bases with small files

Previously we split all markdown files by their headings,
even if the file was small enough to fit entirely within the max token
limits of the search model. This used to reduce the context available
to select the appropriate entries for a given query for the search model,
especially from short knowledge trees
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
d8f01876e5 Add parent heading ancestory to extracted markdown entries for context
Improve, update the markdown to entries extractor tests
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
86575b2946 Chunk text in preference order of para, sentence, word, character
- Previous simplistic chunking strategy of splitting text by space
  didn't capture notes with newlines, no spaces. For e.g in #620

- New strategy will try chunk the text at more natural points like
  paragraph, sentence, word first. If none of those work it'll split
  at character to fit within max token limit

- Drop long words while preserving original delimiters

Resolves #620
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
a627f56a64 Remove unused Entry to Jsonl converter from text to entry class, tests
This was earlier used when the index was plaintext jsonl file. Now
that documents are indexed in a DB this func is not required.

Simplify org,md,pdf,plaintext to entries tests by removing the entry
to jsonl conversion step
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
28105ee027 Create wrapper function to get entries from org, md, pdf & text files
- Convert extract_org_entries function to actually extract org entries
  Previously it was extracting intermediary org-node objects instead
  Now it extracts the org-node objects from files and converts them
  into entries
- Create separate, new function to extract_org_nodes from files
- Similarly create wrapper funcs for md, pdf, plaintext to entries

- Update org, md, pdf, plaintext to entries tests to use the new
  simplified wrapper function to extract org entries
2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
f01a12b1d2 Improve styling of chat sessions side panel
- Move green server connected dot to the bottom. Show status when
  disconnected from server
- Move "New conversation" button to right of the "Conversation" title
- Center alignment of the new conversation and connection status buttons
2024-04-04 01:43:26 +05:30
sabaimran
dd1e5e145a Use List[Any] for typing 2024-04-03 21:46:41 +05:30
sabaimran
b8087c4c8e Add typing to empty list variables in github_to_entries 2024-04-03 21:41:36 +05:30
sabaimran
d036fdfc26 If tree is not in the contents, then just return empty files list 2024-04-03 17:55:25 +05:30
Debanjum Singh Solanky
f915b2bd14 Fix passing model_name param to chatml formatter for online chat 2024-04-03 17:21:43 +05:30
sabaimran
6aa88761b8 Skip creating the default agent if there's no default conversation config 2024-04-03 17:21:01 +05:30
sabaimran
b4f71e06b3 Add timeout after 10 minutes of inactivity on socket 2024-04-02 22:12:27 +05:30
sabaimran
f48426623d resolve merge conflict in chat.html 2024-04-02 17:29:48 +05:30
sabaimran
bf1187f465 Use new online/websearch logic and add agent to chat_metadata 2024-04-02 17:20:38 +05:30
sabaimran
867e1007d1 Remove superfluous newline 2024-04-02 17:20:08 +05:30
sabaimran
228ad68042 Merge with origin/master 2024-04-02 17:02:21 +05:30
sabaimran
776550d5ce Add a migration for updating the default chat model, update for existing users 2024-04-02 17:01:31 +05:30
sabaimran
47fc7e1ce6 Rebase with matser 2024-04-02 16:16:06 +05:30
Debanjum
215ab6e66a
Extract More Dates from entries to improve Date Filter (#683)
- Overview
  - Extract more structured date variants (e.g with dot(.) & slash(/) separators, 2-digit year)
  - Extract some natural, partial dates as well from entries
- Capability
  Add ability to extract the following additional date forms:
  - Natural Dates: 21st April 2000, February 29 2024
  - Partial Natural Dates: March 24, Mar 2024
  - Structured Dates: 20/12/24, 20.12.2024, 2024/12/20
  Note: Previously only YYYY-MM-DD ISO-8601 structured date form was extracted for date filters
- Performance
  Using regexes is MUCH faster than using the `dateparser' python library
  It's a little crude but gives acceptable performance for large datasets
2024-04-02 16:14:53 +05:30
Debanjum Singh Solanky
7afee2d55c Let offline chat model set context window. Improve, fix prompts 2024-03-31 16:19:35 +05:30
Debanjum Singh Solanky
4228965c9b Handle msg truncation when question is larger than max prompt size
Notice and truncate the question it self at this point
2024-03-31 15:50:06 +05:30
Debanjum Singh Solanky
886d49e3a4 Merge branch 'master' into migrate-to-llama-cpp-for-offline-chat 2024-03-31 00:59:20 +05:30
Debanjum Singh Solanky
4f65dde201 Release Khoj version 1.8.0 2024-03-31 00:06:15 +05:30
Debanjum Singh Solanky
7923903d21 Improve date filter regexes to extract structured, natural, partial dates
- Much faster than using dateparser
  - It took 2x-4x for improved regex to extracts 1-15% more dates
  - Whereas It took 33x to 100x for dateparser to extract 65% - 400% more dates
  - Improve date extractor tests to test deduping dates, natural,
    structured date extraction from content

- Extract some natural, partial dates and more structured dates
  Using regex is much faster than using dateparser. It's a little
  crude but should pay off in performance.

  Supports dates of form:
  - (Day-of-Month) Month|AbbreviatedMonth Year|2DigitYear
  - Month|AbbreviatedMonth (Day-of-Month) Year|2DigitYear
2024-03-30 00:07:19 +05:30
Debanjum Singh Solanky
104eeea274 Extract natural language and locale specific dates in content
Previously we just extracted dates in YYYY-MM-DD format from content
for date filterings during search.

Use dateparser to extract dates across locales and natural language

This should improve notes returned as context when chat searches
knowledge base with date filters

Fallback to regex for date parsing from content if dateparser fails

- Limit natural date extractor capabilities to improve performance
  - Assume language is english
    Language detection otherwise takes a REALLY long time
  - Do not extract unix timestamps, timezone
    - This isn't required, as just using date and approximating dates as UTC
2024-03-30 00:06:56 +05:30
sabaimran
1195f843a3 Remove forward slash from the root agents endpoint 2024-03-28 23:06:55 +05:30
sabaimran
a1729b9b9e Add telemetry for agents used in conversation, increase image width in agents page 2024-03-28 22:18:11 +05:30
sabaimran
d503b3e867 Use Personality vernacular in agent page
- When setting up the default agent, configure every conversation that doesn't have an agent to use the Khoj agent
- Fix reverse migration for the locale removal migration
2024-03-28 15:07:02 +05:30
sabaimran
e59de8c9b1 Constrain width/size of agent image in agents view 2024-03-28 13:32:11 +05:30
sabaimran
51d0c9b8b0 Add telemetry to keep state of new agents being used 2024-03-28 11:37:24 +05:30
sabaimran
46ebc55e2b Add a top tab for agents 2024-03-28 11:37:01 +05:30
sabaimran
8397187231 Use default agent when creating a new conversation without agent specified 2024-03-28 11:36:27 +05:30
Debanjum Singh Solanky
4912c0ee30 Use extract queries actor to improve notes search with offline chat
Previously we were skipping the extract questions step for offline
chat as default offline chat model wasn't good enough to output proper
json given the time it took to extract questions.

The new default offline chat models gives json much more regularly and
with date filters, so the extract questions step becomes useful given
the impact on latency
2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
1ebd5c3648 Rename GPT4AllChatProcessor* to OfflineChatProcessor Config, Model 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
2a0b943bb4 Use Hermes-2-Pro as default offline chat model in khoj.yml 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
8ca39a436c Use llama.cpp for offline chat models
- Benefits of moving to llama-cpp-python from gpt4all:
  - Support for all GGUF format chat models
  - Support for AMD, Nvidia, Mac, Vulcan GPU machines (instead of just Vulcan, Mac)
  - Supports models with more capabilities like tools, schema
    enforcement, speculative ddecoding, image gen etc.
- Upgrade default chat model, prompt size, tokenizer for new supported
  chat models

- Load offline chat model when present on disk without requiring internet
  - Load model onto GPU if not disabled and device has GPU
  - Load model onto CPU if loading model onto GPU fails
  - Create helper function to check and load model from disk, when model
    glob is present on disk.

    `Llama.from_pretrained' needs internet to get repo info from
    HuggingFace. This isn't required, if the model is already downloaded

    Didn't find any existing HF or llama.cpp method that looked for model
    glob on disk without internet
2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
0a7392f6ec Only add location to image prompt generator when location known 2024-03-26 22:33:01 +05:30
sabaimran
fdf78525b4
Part 2: Add web UI updates for basic agent interactions (#675)
* Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications

* Customize default behaviors for conversations without agents or with default agents

* Add a new web client route for viewing all agents

* Use agent_id for getting correct agent

* Add web UI views for agents
- Add a page to view all agents
- Add slugs to manage agents
- Add a view to view single agent
- Display active agent when in chat window
- Fix post-login redirect issue

* Fix agent view

* Spruce up the 404 page and improve the overall layout for agents pages

* Create chat actor for directly reading webpages based on user message

- Add prompt for the read webpages chat actor to extract, infer
  webpage links
- Make chat actor infer or extract webpage to read directly from user
  message
- Rename previous read_webpage function to more narrow
  read_webpage_at_url function

* Rename agents_page -> agent_page

* Fix unit test for adding the filename to the compiled markdown entry

* Fix layout of agent, agents pages

* Merge migrations

* Let the name, slug of the default agent be Khoj, khoj

* Fix chat-related unit tests

* Add webpage chat command for read web pages requested by user

Update auto chat command inference prompt to show example of when to
use webpage chat command (i.e when url is directly provided in link)

* Support webpage command in chat API

- Fallback to use webpage when SERPER not setup and online command was
  attempted
- Do not stop responding if can't retrieve online results. Try to
  respond without the online context

* Test select webpage as data source and extract web urls chat actors

* Tweak prompts to extract information from webpages, online results

- Show more of the truncated messages for debugging context
- Update Khoj personality prompt to encourage it to remember it's capabilities

* Rename extract_content online results field to webpages

* Parallelize simple webpage read and extractor

Similar to what is being done with search_online with olostep

* Pass multiple webpages with their urls in online results context

Previously even if MAX_WEBPAGES_TO_READ was > 1, only 1 extracted
content would ever be passed.

URL of the extracted webpage content wasn't passed to clients in
online results context. This limited them from being rendered

* Render webpage read in chat response references on Web, Desktop apps

* Time chat actor responses & chat api request start for perf analysis

* Increase the keep alive timeout in the main application for testing

* Do not pipe access/error logs to separate files. Flow to stdout/stderr

* [Temp] Reduce to 1 gunicorn worker

* Change prod docker image to use jammy, rather than nvidia base image

* Use Khoj icon when Khoj web is installed on iOS as a PWA

* Make slug required for agents

* Simplify calling logic and prevent agent access for unauthenticated users

* Standardize to use personality over tuning in agent nomenclature

* Make filtering logic more stringent for accessible agents and remove unused method:

* Format chat message query

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
2024-03-26 18:13:24 +05:30
Debanjum Singh Solanky
15ed208996 Use Khoj icon when Khoj web is installed on iOS as a PWA 2024-03-26 00:13:12 +05:30
Debanjum
586654e2af
Allow directly reading web pages, even when SERP not enabled (#676)
### Overview
Khoj can now read website directly without needing to go through the search step first

### Details
- Parallelize simple webpage read and extractor
- Rename extract_content online results field to web pages
- Tweak prompts to extract information from webpages, online results
- Test select webpage as data source and extract web urls chat actors

- Render webpage read in chat response references on Web, Desktop apps
- Pass multiple webpages with their urls in online results context

- Support webpage command in chat API
- Add webpage chat command for read web pages requested by user
- Create chat actor for directly reading webpages based on user message
2024-03-24 16:25:25 +05:30
Debanjum Singh Solanky
9e52ae9e98 Time chat actor responses & chat api request start for perf analysis 2024-03-24 15:47:38 +05:30
Debanjum Singh Solanky
dabf71bc3c Render webpage read in chat response references on Web, Desktop apps 2024-03-24 15:47:38 +05:30
Debanjum Singh Solanky
a2e79c94be Pass multiple webpages with their urls in online results context
Previously even if MAX_WEBPAGES_TO_READ was > 1, only 1 extracted
content would ever be passed.

URL of the extracted webpage content wasn't passed to clients in
online results context. This limited them from being rendered
2024-03-24 15:47:38 +05:30
Debanjum Singh Solanky
71b6905008 Parallelize simple webpage read and extractor
Similar to what is being done with search_online with olostep
2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
1167f6ddf9 Rename extract_content online results field to webpages 2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
b22a7dae5d Tweak prompts to extract information from webpages, online results
- Show more of the truncated messages for debugging context
- Update Khoj personality prompt to encourage it to remember it's capabilities
2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
ad6f6bb0ed Support webpage command in chat API
- Fallback to use webpage when SERPER not setup and online command was
  attempted
- Do not stop responding if can't retrieve online results. Try to
  respond without the online context
2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
a6b7432837 Add webpage chat command for read web pages requested by user
Update auto chat command inference prompt to show example of when to
use webpage chat command (i.e when url is directly provided in link)
2024-03-24 15:46:29 +05:30
sabaimran
8abc8ded82
Part 1: Server-side changes to support agents integrated with Conversations (#671)
* Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications

* Customize default behaviors for conversations without agents or with default agents

* Use agent_id for getting correct agent

* Merge migrations

* Simplify some variable definitions, add additional security checks for agents

* Rename agent.tuning -> agent.personality
2024-03-23 22:09:38 +05:30
sabaimran
4deb849fb1 Merge branch 'features/add-agents-ui' of github.com:khoj-ai/khoj into features/chat-socket-streaming 2024-03-23 14:04:25 +05:30
sabaimran
8edbd7094f Let the name, slug of the default agent be Khoj, khoj 2024-03-23 14:03:58 +05:30
sabaimran
6b4c4f10b5 Merge branch 'features/add-agents-ui' of github.com:khoj-ai/khoj into features/chat-socket-streaming 2024-03-23 11:22:00 +05:30
sabaimran
20617614ae Merge branch 'features/customize-chat-with-agents' of github.com:khoj-ai/khoj into features/add-agents-ui 2024-03-23 11:20:57 +05:30
sabaimran
2399d91f61 Merge migrations 2024-03-22 10:05:33 +05:30
sabaimran
d38089ab57 Merge with origin 2024-03-22 09:55:33 +05:30
Debanjum Singh Solanky
aed4313cfc Fix updating specific conversation by id from the chat API endpoint
- Use the conversation id of the retrieved conversation rather than the
  potentially unset conversation id passed via API
- await creating new chat when no chat id provided and no existing
  conversations exist
2024-03-21 02:46:52 +05:30
sabaimran
6ba0d8e379 Add a connected notification if the websocket is connected 2024-03-20 20:53:28 +05:30
sabaimran
255b69dc58 Add a comma delimeter between outputted search queries 2024-03-20 19:43:35 +05:30
sabaimran
d84188b221 Scroll down when a message is added in the chat interface's handle stream response method 2024-03-20 15:04:41 +05:30
sabaimran
70ad78990a Use a common method for sending a generic message to the client from the server in the ws connection 2024-03-20 15:04:14 +05:30
sabaimran
d4e83b060a Update the web UI for the chat interface to establish a connection via a socket to the server
- Move some common methods into separate functions to make the UI components more efficient
- The normal HTTP-based chat connection will still work and serves as a fallback if the websocket is unavailable
2024-03-20 14:34:47 +05:30
sabaimran
a346f79b39 Add support for chatting via the web socket connection
- Convert to a model of calling the search API directly with a function call (rather than using the API method)
- Gracefully handle websocket connection disconnects
- Ensure that the rest of the response is still saved, as it is currently, if the user disconects from the client
- Setup unchangeable context at the beginning of the session when the connection is established (like location, username, etc)
2024-03-20 14:33:33 +05:30
Debanjum Singh Solanky
62a83dc9bb Fix online search actor to use natural dates not after: operator
The recently added after: operator to online search actor was too
restrictive, gave worse results than when just use natural language
dates in search query
2024-03-15 21:50:14 +05:30
Debanjum Singh Solanky
4a1e6a2275 Convert deleted old user requests log line to debug from info 2024-03-15 20:50:10 +05:30
Debanjum Singh Solanky
9a068dadbf Fix extract questions prompt to use YYYY-MM-DD date filter format 2024-03-15 18:43:18 +05:30
Debanjum Singh Solanky
ecddf98430 Handle truncation when single long non-system chat message
Previously was assuming the system prompt is being always passed as
the first message. So expected there to be at least 2 messages in logs.

This broke chat actors querying with single long non system message.

A more robust way to extract system prompt is via the message role
instead
2024-03-15 15:58:39 +05:30
Debanjum Singh Solanky
ec0c35b7ed Improve delete, rename chat session UX in Desktop, Web app
- Ask for Confirmation before deleting chat session in Desktop, Web app
- Save chat session rename on hitting enter in title edit input box
- No need to flash previous conversation cleared status message
- Move chat session delete button after rename button in Desktop app
2024-03-15 15:58:19 +05:30
Debanjum Singh Solanky
924b1215ce Allow unset locale for Google authenticated user 2024-03-15 15:35:20 +05:30
Debanjum Singh Solanky
c792fa819f Fix setting chat session title from Desktop app
Pass auth headers to not have the chat session title update request fail
2024-03-15 15:19:20 +05:30
Debanjum Singh Solanky
c9e05dc184 Get conversation by title when requested via chat API 2024-03-15 12:31:50 +05:30
sabaimran
724557fc7b Merge branch 'master' of github.com:khoj-ai/khoj into features/add-agents-ui 2024-03-15 12:14:34 +05:30
sabaimran
7fc484ba7a Merge branch 'master' of github.com:khoj-ai/khoj into features/customize-chat-with-agents 2024-03-15 12:13:28 +05:30
Debanjum Singh Solanky
cac26dafe3 Only create new chat on get if a specific chat id, slug isn't requested 2024-03-15 11:58:39 +05:30
sabaimran
416feb13ef Fix layout of agent, agents pages 2024-03-15 11:17:40 +05:30
sabaimran
d734be61cf Rename agents_page -> agent_page 2024-03-15 10:17:51 +05:30
Debanjum Singh Solanky
08993ff109 Add new, remove old known chat models from model to prompt size map 2024-03-15 04:02:25 +05:30
Debanjum Singh Solanky
fba0338787 Release Khoj version 1.7.0 2024-03-15 00:08:32 +05:30
Debanjum Singh Solanky
6118d1ff57 Create chat actor for directly reading webpages based on user message
- Add prompt for the read webpages chat actor to extract, infer
  webpage links
- Make chat actor infer or extract webpage to read directly from user
  message
- Rename previous read_webpage function to more narrow
  read_webpage_at_url function
2024-03-14 14:58:37 +05:30
Debanjum
e549824fe2
Improve OpenAI Chat Actors and their prompts (#673)
### Major
- Enforce json mode response from OpenAI chat actors prev using string lists
- Use `gpt-4-turbo-preview' as default chat model, extract questions actor
- Make Khoj read khoj website to respond with accurate, up-to-date information about itself
- Dedupe query in notes prompt. Improve OAI chat actor, director tests

### Minor
- Test data source, output mode selector, web search query chat actors
- Improve notes search actor to always create a non-empty list of queries
- Construct available data sources, output modes as a bullet list in prompts
- Use consistent agent name across static and dynamic examples in prompts
- Add actor's name to extract questions prompt to improve context for guidance
2024-03-14 12:44:40 +05:30
sabaimran
3caf0a79d8 Spruce up the 404 page and improve the overall layout for agents pages 2024-03-14 11:26:49 +05:30
sabaimran
c45030af44 Fix agent view 2024-03-14 11:13:19 +05:30
Debanjum Singh Solanky
a1ce12296f Fix rendering online with note references post streaming chat response
Previously only the notes references would get rendered post response
streaming when when both online and notes references were used to
respond to the user's message
2024-03-14 03:40:40 +05:30
Debanjum Singh Solanky
1aeea3d854 Fix opening external links from confirmation dialog box on desktop app 2024-03-14 02:29:22 +05:30
Debanjum Singh Solanky
2e5cc49cb3 Enforce json response from OpenAI chat actors prev using string lists
- Allow passing response format type to OpenAI API via chat actors
- Convert in-context examples to use json objects instead of str lists
- Update actors outputting str list to request output to be json_object
  - OpenAI's json mode enforces the model to output valid json object
2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
7211eb9cf5 Default to gpt-4-turbo-preview for chat model, extract questions actor
GPT-4 is more expensive and generally less capable than gpt-4-turbo-preview
2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
dd883dc53a Dedupe query in notes prompt. Improve OAI chat actor, director tests
- Remove stale tests
- Improve tests to pass across gpt-3.5 and gpt-4-turbo
- The haiku creation director was failing because of duplicate query in
  instantiated prompt
2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
14682d5354 Improve notes search actor to always create a non-empty list of queries
- Remove the option for Notes search query generation actor to return
  no queries. Whether search should be performed is decided before,
  this step doesn't need to decide that
- But do not throw warning if the response is a list with no elements
2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
f5734826cb Improve pick data source prompt to look online for info about Khoj
- Add examples where user queries requesting information about Khoj
  results in the "online" data source being selected
- Add an example for "general" to select chat command prompt
2024-03-14 01:21:13 +05:30
Debanjum Singh Solanky
9a516bed47 Construct available data sources, output modes as a bullet list in prompts 2024-03-14 00:34:57 +05:30
Debanjum Singh Solanky
f28fb89af8 Use consistent agent name across static and dynamic examples in prompts
Previously the examples constructed from chat history used "Khoj" as
the agent's name but all 3 prompts using the func used static examples
with "AI:" as the pertinent agent's name
2024-03-14 00:34:57 +05:30
Debanjum Singh Solanky
f5793149a9 Add actor's name to extract questions prompt to improve context for guidance 2024-03-14 00:34:57 +05:30
Debanjum Singh Solanky
73ad444086 Make online search Actor read khoj.dev for docs, info about Khoj
- Add example to read khoj.dev website for up-to-date info to setup,
  use khoj, discover khoj features etc.
- Online search should use site: and after: google search operators
  - Show example of adding the after: date filter to google search
- Give local event lookup example using user's current location in
  query
- Remove unused select search content type prompt
2024-03-14 00:34:57 +05:30
sabaimran
290712c3fe Add web UI views for agents
- Add a page to view all agents
- Add slugs to manage agents
- Add a view to view single agent
- Display active agent when in chat window
- Fix post-login redirect issue
2024-03-14 00:07:36 +05:30
Debanjum
3abe7ccb26
Improve Online Search Speed and Context (#670)
### Major
- Read web pages in parallel to improve chat response time
- Read web pages directly when Olostep proxy not setup
- Include search results & web page content in online context for chat response

### Minor
- Simplify, modularize and add type hints to online search functions
2024-03-11 22:16:30 +05:30
Debanjum Singh Solanky
dc86e44a07 Include search results & webpage content in online context for chat response
Previously if a web page was read for a sub-query, only the extracted
web page content was provided as context for the given sub-query. But
the google results themselves have relevant snippets. So include them
2024-03-11 18:41:02 +05:30
Debanjum Singh Solanky
d136a6be44 Simplify, modularize and add type hints to online search functions
- Simplify content arg to `extract_relevant_info' function. Validate,
  clean the content arg inside the `extract_relevant_info' function

- Extract `search_with_google' function outside the parent function
- Call the parent function a more appropriate `search_online' instead
  of `search_with_google'
- Simplify the `search_with_google' function using list comprehension.
  Drop empty search result fields from chat model context for response
  to reduce cost and response latency

- No need to show stacktrace when unable to read webpage, basic error
  is enough
- Add type hints to online search functions to catch issues with mypy
2024-03-11 18:41:02 +05:30
Debanjum Singh Solanky
88f096977b Read webpages directly when Olostep proxy not setup
This is useful for self-hosted, individual user, low traffic setups
where a proxy service is not required
2024-03-11 18:41:02 +05:30
Debanjum Singh Solanky
ca2f962e95 Read, extract information from web pages in parallel to lower response time
- Time reading webpage, extract info from webpage steps for perf
  analysis
- Deduplicate webpages to read gathered across separate google
  searches
- Use aiohttp to make API requests non-blocking, pair with asyncio to
  parallelize all the online search webpage read and extract calls
2024-03-11 18:41:02 +05:30
sabaimran
8e1445b15b Use agent_id for getting correct agent 2024-03-11 14:44:46 +05:30
sabaimran
6ab649312f Add a new web client route for viewing all agents 2024-03-11 14:40:40 +05:30
sabaimran
352168d6c2 Customize default behaviors for conversations without agents or with default agents 2024-03-11 14:20:28 +05:30
sabaimran
9b88976f36 Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications
2024-03-11 12:45:24 +05:30
Debanjum
18fa3e2384
Rerank Search Results by Default on GPU machines (#668)
- Trigger
   SentenceTransformer Cross Encoder models now run fast on GPU enabled machines, including Mac ARM devices since UKPLab/sentence-transformers#2463

- Details
  - Use cross-encoder to rerank search results by default on GPU machines and when using an inference server
  - Only call search API when pause in typing search query on web, desktop apps
2024-03-10 15:15:25 +05:30
Debanjum Singh Solanky
53d402480c Rerank search results with cross-encoder when using an inference server
If an inference server is being used, we can expect the cross encoder
to be running fast enough to rerank search results by default
2024-03-10 15:09:46 +05:30
Debanjum Singh Solanky
44c8d09342 Only call search API when pause in typing search query on web, desktop apps
Wait for 300ms since stop typing before calling search API.

This smooths out UI jitter when rendering search results, especially
now that we're reranking for every search query on GPU enabled devices

Emacs already has 300ms debounce time. More convoluted to add
debounce time to Obsidian search modal, so not updating that yet
2024-03-10 14:29:24 +05:30
Debanjum Singh Solanky
1105d8814f Use cross-encoder to rerank search results by default on GPU machines
Latest sentence-transformer package uses GPU for cross-encoder. This
makes it fast enough to enable reranking on machines with GPU.

Enabling search reranking by default allows (at least) users with GPUs
to side-step learning the UI affordance to rerank results
(i.e hitting Cmd/Ctrl-Enter or ENTER).
2024-03-10 14:29:21 +05:30
Debanjum Singh Solanky
fd81446ba3 Do not create new chat session when an old chat session is deleted
- Fix
  `get_conversation_by_user' shouldn't return new conversation if
  conversation with requested id not found.

  It should only return new conversation if no specific conversation
  is requested and no conversations found for user at all

- Repro
  - Delete a new chat, this calls loadChat via window.onload which
    calls server /chat/history API endpoint with conversationId set to
    that of just deleted conversation sporadically

    The call to GET chat/history API with conversationId set occurs
    when window.onload triggers before the conversationId is deleted
    by the delete button after the DELETE /chat/history API call (via race)

  - In such a scenario, get_conversation_by_user called by
    chat/history API with conversationId of deleted conversation
    returns a new conversation

- Miscellaneous
  - Chat history load should be logged as call to that chat_history api,
    not the "chat" api
  - Show status updates of clearing conversation history in chat input
  - Simplify web, desktop client code by removing unnecessary new variables
2024-03-10 02:17:23 +05:30
Debanjum Singh Solanky
b7fad04870 Use consistent field name for queries in chat history & better image prompt 2024-03-09 19:11:03 +05:30
sabaimran
6aae9864d3 Fix Notion indexing and add an admin view for Entry objects 2024-03-09 16:25:23 +05:30
sabaimran
12d6c4da7d Only include inferred queries in the conversation history for images, not links. Overflow the side panel when too long 2024-03-09 11:59:35 +05:30
sabaimran
e5cd0237e3 Release Khoj version 1.6.2 2024-03-08 17:04:03 +05:30
Debanjum Singh Solanky
446ac7649d Remove unused js method in web chat client, add newline to web data in prompt 2024-03-08 16:40:39 +05:30
Debanjum Singh Solanky
12d32ac99c Increase user visibility into more errors during image generation
Catch OpenAI connection error and errors during better image prompt
generation
2024-03-08 16:40:39 +05:30
sabaimran
ff31759423 Fix target determination in the copy programmatic output button 2024-03-08 16:33:12 +05:30
sabaimran
9f934929c6 Infer mime type from file ending when not available in browser. Don't output image in conversation turns 2024-03-08 12:34:26 +05:30
sabaimran
81beb7940c
Upload generated images to s3, if AWS credentials and bucket is available (#667)
* Upload generated images to s3, if AWS credentials and bucket is available.
- In clients, render the images via the URL if it's returned with a text-to-image2 intent type
* Make the loading screen more intuitve, less jerky and update the programmatic copy button
* Update the loading icon when waiting for a chat response
2024-03-08 10:54:13 +05:30
sabaimran
13894e1fd5 add instructions for drag/drop files in sys prompt 2024-03-07 17:57:42 +05:30
sabaimran
7357b6eff1 Revert white-space preline and add more detailed help text when selecting file 2024-03-06 16:47:27 +05:30
sabaimran
b615c0719e
Support upload for files via drag/drop in the web UI (#666)
* Add additional styling changes for showing UI changes when dragging file to the main screen

* Add a loading spinner when file upload is in progress, and don't index github/notion when indexing files

* Add an explicit icon for file uploading in the chat button menu

* Add appropriate dragover styling when picking a file from the file picker/browser

* Add a loading screen when retrieving chat history. Fix width of the chat window. Put attachment icon to the left of chat input
2024-03-06 16:43:05 +05:30
sabaimran
e323a6d69b
Include additional user context in the image generation flow (#660)
* Make major improvements to the image generation flow

- Include user context from online references and personal notes for generating images
- Dynamically select the modality that the LLM should respond with
- Retun the inferred context in the query response for the dekstop, web chat views to read

* Add unit tests for retrieving response modes via LLM

* Move output mode unit tests to the actor suite, rather than director

* Only show the references button if there is at least one available

* Rename aget_relevant_modes to aget_relevant_output_modes

* Use a shared method for generating reference sections, simplify some of the prompting logic

* Make out of space errors in the desktop client more obvious
2024-03-06 13:48:41 +05:30
Debanjum Singh Solanky
2d61591c22 Improve user visibility into errors during image generation 2024-02-29 13:19:13 +05:30
sabaimran
0bbb5cff85 Release Khoj version 1.6.1 2024-02-26 13:27:20 -08:00
sabaimran
c8194a7364 Make out of space errors in the desktop client more obvious 2024-02-26 11:53:36 -08:00
Debanjum Singh Solanky
956dd71d91 Clean entry before adding to DB and log when it fails
Remove \0 null characters from entry fields as this is causing
indexing errors
2024-02-27 01:19:34 +05:30
Debanjum Singh Solanky
bb613a8e1d Make indentation styling more compact on Obsidian client 2024-02-25 14:41:45 +05:30
Debanjum Singh Solanky
682b70011f Set chat body height to remove UX jitter on chat history load in Web, Desktop 2024-02-25 14:40:47 +05:30
Debanjum Singh Solanky
efe86ce159 Fix saved conversation logger to handle image responses 2024-02-25 13:46:32 +05:30
Debanjum Singh Solanky
4839f2901a Open external links in Desktop app with default app for url on OS
- Open external links using the default link handler registered on OS
  for the link type, e.g http:// -> firefox, mailto: thunderbird etc
- Confirm before opening non-http URL using an external app
2024-02-25 13:21:52 +05:30
Debanjum
170bce2c02
Fix, Improve rendering images in Obsidian, Desktop, Web clients (#659)
- Improve render of inferred query in image chat messages in Web, Desktop apps
- Add inferred queries to image chat responses in Obsidian client
- Fix rendering images from Khoj response in Obsidian client
2024-02-25 00:56:26 +05:30
Debanjum Singh Solanky
f84606325c Improve render of inferred query in image chat messages in Web, Desktop apps 2024-02-25 00:47:06 +05:30
Debanjum Singh Solanky
a2e53d5e41 Add inferred queries to image chat responses in Obsidian client 2024-02-25 00:24:58 +05:30
Debanjum Singh Solanky
9b61f0b5f7 Fix rendering images from Khoj response in Obsidian client 2024-02-25 00:11:11 +05:30
sabaimran
b9d0533d92
Misc. fixes to prompting, admin, and others (#658)
* Simplify and clarify prompt for selecting toolset dynamically

* Add error handling around call to OLOSTEP api

* Fix conversation admin page

* Skip adding none or empty entries in the chunking method
2024-02-24 10:25:42 -08:00
Debanjum Singh Solanky
0e0e751ef7 Improve docstring of entrypoint function to the emacs client 2024-02-24 21:09:41 +05:30
Debanjum
8855529637
Improve Syncing Obsidian Vault, Invalidate Static Assets in Browser Cache in Web Client (#657)
- Improve
  - Only send files modified since their last sync for indexing on server from the Obsidian client
- Fix 
  - Invalidate static asset browser cache in Web client when Khoj version changes
2024-02-24 20:20:30 +05:30
Debanjum Singh Solanky
a46f70c4b0 Remove deprecated lastSyncedFiles settings field from Obsidian client 2024-02-24 20:18:22 +05:30
Debanjum Singh Solanky
03a6b491b2 Warn when can't identify mimeType of files in Desktop, Obsidian clients 2024-02-24 19:59:03 +05:30
Debanjum Singh Solanky
3675ab4864 Only sync modified files from the Obsidian client
Previously we'd send all files in vault and let the server
deduplicate.

This changes takes inspiration from the desktop app, and only pushes
files which were modified after their previous sync with the server.

This should reduce the processing load on the server
2024-02-24 07:48:40 +05:30
Debanjum Singh Solanky
ddfbf31bc8 Append version query param to web asset URLs to bypass browser cache
Ensure latest assets are loaded when khoj version is updated
2024-02-24 06:49:25 +05:30
sabaimran
42773e808c
Retrieve, create, and save conversations differently for ClientApplications (#656)
* Retrieve, create, and save conversations differently if they're coming from a client application

- Not all of our client apps will necessarily maintain state over the conversation IDs available to a user. For some (single-threaded conversations), it should just use a single conversation. Fix the code to do so

* Simplify conversation retrieval logic

* Keep 0 padding below chat response

* Add order_by sorting to retrieving the conversation without id
2024-02-23 11:32:00 -08:00
Debanjum
9afb2a14ef
Fix and Improve Chat UI in Web, Desktop apps (#655)
### Improvements to Chat UI on Web, Desktop apps
- Improve styling of chat session side panel
- Improve styling of chat message bubble in Desktop, Web app
- Add frosted, minimal chat UI to background of Login screen
- Improve PWA install experience of Khoj

### Fixes to Chat UI on Web, Desktop apps
- Fix creating new chat sessions from the Desktop app
- Only show 3 starter questions even when consecutive chat sessions created

### Other Improvements
- Update Khoj cloud trial period to a fortnight instead of a week
- Document using venv to handle dependency conflict on khoj pip install

Resolves #276
2024-02-23 19:27:02 +05:30
Debanjum Singh Solanky
c70ca78cdc Improve PWA install experience for Khoj on Desktop, Mobile
- Resolve PWA issues thrown by Chrome/Edge
  - Add screenshot samples showcasing remember, browse and draw features
    - This can provide a richer app store like experience when
      installing Khoj PWA on Mobile or Desktop
    - Add wide and narrow screenshots to show Mobile vs Desktop UX
  - Add higher resolution favicon for PWA
- Use single web manifest instead of separate ones for Chat, Search
- Update manifest description with more details about Khoj features
2024-02-23 18:59:52 +05:30
Debanjum Singh Solanky
e10b260988 Update web login screen to show frosted minimal chat UI in background 2024-02-23 18:59:52 +05:30
Debanjum Singh Solanky
1b0318564e Log when conversation turn is saved to DB 2024-02-23 18:59:52 +05:30
Debanjum Singh Solanky
4c39960917 Make number of conversation starters to get from DB configurable 2024-02-23 18:59:52 +05:30
Debanjum Singh Solanky
50617594fd Only show 3 starter questions even when consecutive chat sessions created
Reset starter question suggestions before appending in web, desktop app

Otherwise previously it'd keep adding to existing starter question
suggestions on each new session creation if multiple consecutive new
chat sessions created.

This would result in more than the 3 expected starter questions being
displayed at a time
2024-02-23 18:59:52 +05:30
Debanjum Singh Solanky
102f5c3f53 Improve styling of chat session side panel
- Make collapse, expand toggle arrow point in the direction the action
  will expand the side panel in
- Make the collapsed side panel reduce to a 1px sliver
2024-02-23 18:59:52 +05:30
Debanjum Singh Solanky
6283d9fe83 Update Khoj cloud trial period to a fortnight instead of a week
- Improve rate limit error message wording
- Make the "too many requests" error message more robust. Should throw
  that exception fix self.request >= self.subscribed_requests because
  upgrading wouldn't fix this rate limiting
2024-02-23 18:33:56 +05:30
Debanjum Singh Solanky
05c1903784 Fix creating new chat sessions from the Desktop app
Code wasn't passing the authorization header in the POST request to
create new chat session
2024-02-23 18:33:56 +05:30
Debanjum Singh Solanky
8a219b6e9c Improve styling of chat message bubble in Desktop, Web app
- Respect newline with pre-line but not for bullets to improve
  formatting of responses by Khoj
- Respect bold font by loading tajawal font with other weights
- Reduce bottom margin in chat message bubble, its taking too much space
2024-02-23 18:33:56 +05:30
sabaimran
b4902090e7
Misc. chat and application improvements (#652)
* Document original query when subqueries can't be generated
* Only add messages to the chat message log if it's non-empty
* When changing the search model, alert the user that all underlying data will be deleted
* Adding more clarification to the prompt input for username, location
* Check if has_more is in the notion results before getting next_cursor
* Update prompt template for user name/location, update confirmation message when changing search model
2024-02-22 19:09:22 -08:00
Debanjum Singh Solanky
7271164256 Set chat session title to textContent of the chat session HTML element
We don't expect/want the user to use HTML titles for chat session
2024-02-23 02:07:08 +05:30
sabaimran
f8ec6b4464 Remove backslash for default route in api_chat 2024-02-20 20:09:44 -08:00
sabaimran
b1c86fee3b Release Khoj version 1.6.0 2024-02-20 14:12:24 -08:00
sabaimran
44f8f20ea7
Miscellaneous bugs and fixes for chat sessions (#646)
* Display given_name field only if it is not None

* Add default slugs in the migration script

* Ensure that updated_at is saved appropriately, make sure most recent chat is returned for default history

* Remove the bin button from the chat interface, given deletion is handled in the drop-down menus

* Refresh the side panel when a new chat is created

* Improveme tool retrieval prompt, don't let /online fail, and improve parsing of extract questions

* Fix ending chat response by offline chat on hitting a stop phrase

Previously the whole phrase wouldn't be in the same response chunk, so
chat response wouldn't stop on hitting a stop phrase

Now use a queue to keep track of last 3 chunks, and to stop responding
when hit a stop phrase

* Make chat on Obsidian backward compatible post chat session API updates

- Make chat on Obsidian get chat history from
  `responseJson.response.chat' when available (i.e when using new api)
- Else fallback to loading chat history from
  responseJson.response (i.e when using old api)

* Fix detecting success of indexing update in khoj.el

When khoj.el attempts to index on a Khoj server served behind an https
endpoint, the success reponse status contains plist with certs. This
doesn't mean the update failed.

Look for :errors key in status instead to determine if indexing API
call failed. This fixes detecting indexing API call success on the
Khoj Emacs client, even for Khoj servers running behind SSL/HTTPS

* Fix the mechanism for populating notes references in the conversation primer for both offline and online chat

* Return conversation.default when empty list for dynamic prompt selection, send all cmds in telemetry

* Fix making chat on Obsidian backward compatible post chat session API updates

New API always has conversation_id set, not `chat' which can be unset
when chat session is empty.

So use conversation_id to decide whether to get chat logs from
`responseJson.response.chat' or `responseJson.response' instead

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
2024-02-20 13:55:35 -08:00
sabaimran
138f5223bd
Fix process for generating embeddings for Notion entries (#648)
* Fix process for generating embeddings for Notion entries
* If no title field found, just log a warning and set the title to
2024-02-20 13:46:56 -08:00
Debanjum Singh Solanky
4722da9642 Only enable API token, Whatsapp cards on Web UI when Stripe, Twilio setup 2024-02-16 17:41:09 +05:30
Debanjum Singh Solanky
cf4a524988 Move production dependencies to prod python packages group
This will reduce khoj dependencies to install for self-hosting users

- Move auth production dependencies to prod python packages group
  - Only enable authentication API router if not in anonymous mode
  - Improve error with requirements to enable authentication when not in
    anonymous mode
2024-02-16 17:41:08 +05:30
Debanjum Singh Solanky
d7dbb715ef Fix docs links in khoj introductory chat message 2024-02-13 22:38:03 +05:30
sabaimran
32ec54172e
Add additional personalization in Chat via Location, Username (#644)
* Add location metadata to chat history
* Add support for custom configuration of the user name
* Add region, country, city in the desktop app's URL for context in chat
* Update prompts to specify user location, rather than just location.
* Add location data to Obsidian chat query
* Use first word for first name, last word for last name when setting profile name
2024-02-13 17:05:13 +05:30
sabaimran
a3eb17b7d4
Have Khoj dynamically select conversation command(s) in chat (#641)
* Have Khoj dynamically select which conversation command(s) are to be used in the chat flow
- Intercept the commands if in default mode, and have Khoj dynamically guess which tools would be the most relevant for answering the user's query
* Remove conditional for default to enter online search mode
* Add multiple-tool examples in the prompt, make prompt for tools more specific to info collection
2024-02-11 17:11:32 +05:30
sabaimran
69344a6aa6
Add support for multiple chat sessions in the desktop application (#639)
* Add chat sessions to the desktop application
* Increase width of the main chat body to 90vw
* Update the version of electron
* Render the default message if chat history fails to load
* Merge conversation migrations and fix slug setting
* Update the welcome message, use the hostURL, and update background color for chat actions
* Only update the window's web contents if the page is config
2024-02-11 16:05:28 +05:30
sabaimran
1412ed6a00
Support multiple chat sessions within the web UI (#638)
* Enable support for multiple chat sessions within the web client

- Allow users to create multiple chat sessions and manage them
- Give chat session slugs based on the most recent message
- Update web UI to have a collapsible menu with active chats
- Move chat routes into a separate file

* Make the collapsible side panel more graceful, improve some styling elements of the new layout

* Support modification of the conversation title

- Add a new field to the conversation object
- Update UI to add a threedotmenu to each conversation

* Get the default conversation if a matching one is not found by id
2024-02-11 15:48:28 +05:30
Debanjum Singh Solanky
70f74cde68 Fix timestamps to separate each logline. Info log response start time 2024-02-07 20:45:16 +05:30
Debanjum Singh Solanky
8e5db72140 Release Khoj version 1.5.1 2024-02-06 23:09:33 +05:30
Debanjum
fc1b8f6fb6
Fix Khoj Obsidian plugin on Obsidian Mobile (#635)
- Removed node-fetch dependency to work on mobile. 
- Fix CORS issue for Khoj (streaming) chat on Obsidian mobile
- Verified Khoj plugin, search, chat work on Obsidian mobile.

## Details
### Major
- Allow calls to Khoj server from Obsidian mobile app to fix CORS issue
- Chat stream using default `fetch' not `node-fetch' in obsidian plugin

### Minor
- Load chat history after other elements in chat modal on Obsidian are rendered
- Scroll to bottom of chat modal on Obsidian across mobile & desktop
2024-02-06 22:03:51 +05:30
Debanjum Singh Solanky
fd238ff792 Load chat history after other elements in chat modal on Obsidian rendered
This reduces laggy feeling due to latency of loading chat history from
server
2024-02-06 21:25:43 +05:30
Debanjum Singh Solanky
e06a0c6ae0 Scroll to bottom of chat modal on Obsidian across mobile & desktop
Put logic into single reused function
2024-02-06 21:25:43 +05:30
Debanjum Singh Solanky
07dc04f40e Allow calls to Khoj server from Obsidian mobile app to fix CORS issue
- Obsidian mobile uses capacitor js. Requests from it have origin as
  http://localhost on Android and capacitor://localhost on iOS
- Allow those Obsidian mobile origins in CORS middleware of server
2024-02-06 21:25:43 +05:30
Debanjum Singh Solanky
dd4cf66be1 Improve offline chat system prompt to think step by step 2024-02-06 20:23:19 +05:30
Debanjum Singh Solanky
035165b534 Make offline chat model current date aware. Improve system prompts
- Can now expect date awareness chat quality test to pass
- Prevent offline chat model from printing verbatim user Notes and
  special tokens
- Make it ask follow-up questions if it needs more context
2024-02-06 20:23:19 +05:30
Debanjum Singh Solanky
447904f0ab Chat stream using default fetch' not node-fetch' in obsidian plugin
Plugins using NodeJS libraries like `node-fetch' don't work on
Obsidian mobile
2024-02-06 03:03:42 +05:30
Debanjum Singh Solanky
ba79334863 Only log number of day old user requests, not the complete dictionary 2024-02-02 10:33:31 +05:30
Debanjum Singh Solanky
1c6f1d94f5 Fix styling of Whatsapp card & notify banner in config page of web app
- Put Whatsapp card back in Client section.
  - Fixes side spacing on cards
  - Improve Whatsapp card row gaps

- Hide notification banner on web app load. Previously it showed up as
  a yellow dot on smaller displays
2024-02-01 22:59:57 +05:30
sabaimran
4daac334bc
Fix subscription state detection for users based on phone numbers, emails (#633)
* Fix subscription state detection for users based on phone numbers, emails
* Fix unit tests for api_user4
* Use a single method for determining subscription from user
* Pass user object, rather than user.email for getting subscription state
2024-01-31 07:48:55 +05:30
sabaimran
fc4b57d9f6 Revert styling for white-space pre-line in the chat views as it looks bad 2024-01-29 18:29:54 +05:30
sabaimran
da854703aa Release Khoj version 1.5.0 2024-01-29 18:05:10 +05:30
Debanjum
d1bfb245df
Improve Khoj Chat and Settings UI (#630)
* Fix license in pyproject.toml. Remove unused utils.state import

* Use single debug mode check function. Disable telemetry in debug mode

- Use single logic to check if khoj is running in debug mode.
  Previously there were 3 different variants of the check

- Do not log telemetry if KHOJ_DEBUG is set to true. Previously didn't
log telemetry even if KHOJ_DEBUG set to false

* Respect line breaks in user, khoj chat messages to improve formatting

* Disable Whatsapp config section on web client if Twilio not configured

Simplify Whatsapp configuration status checking js by standardizing
external input to lower case

* Disable Phone API when Twilio not setup and rate limit calls to it

- Move phone api to separate router and only enable it if Twilio enabled
- Add rate-limiting to OTP and verification calls

* Add slugs for phone rate limiting

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-01-29 18:03:43 +05:30
sabaimran
4fb8d5c6d4
Store rate limiter-related metadata in the database for more resilience (#629)
* Store rate limiter-related metadata in the database for more resilience
- This helps maintain state even between server restarts
- Allows you to scale up workers on your service without having to implement sticky routing
* Make the usage exceeded message less abrasive
* Fix rate limiter for specific conversation commands and improve the copy
2024-01-29 15:27:06 +05:30
sabaimran
71cbe5160d
Add retries in case the embeddings API fails (#628)
* Add retries in case the embeddings API fails
* Improve error handling in the inference endpoint API request handler
- retry only if HTTP exception
- use logger to output information about errors
2024-01-29 15:26:34 +05:30
sabaimran
b782683e60
Scrape results from Serper results using Olostep (#627)
* Initailize changes to incporate web scraping logic after getting SERP results
- Do some minor refactors to pass a symptom prompt to the openai model when making a query
- integrate Olostep in order to perform the webscraping
* Fix truncation error with new line, fix typing in olostep code
* Use the authorization header for the token
* Add a small hint/indicator for how to use Khojs other modalities in the welcome prompt
* Add more detailed error message if Olostep query fails
* Add unit tests which invoke Olostep in chat director
* Add test for olostep tool
2024-01-29 14:16:50 +05:30
sabaimran
360b59cdb2 Add handling for None field values in logs and make telemetry upload more frequent 2024-01-26 00:00:55 +05:30
sabaimran
737fb6417b Revert none checking in telemetry logs 2024-01-25 23:48:09 +05:30
sabaimran
211c5623e8 Improve error handling for telemetry uploads
- Use response.raise_for_status when telemetry upload files
- Do not send null packets to the destination server
2024-01-25 20:40:42 +05:30
Debanjum Singh Solanky
098a8e4fb1 Fix evaluating connected to server status in Obsidian plugin
Only show welcome status message when khojApiKey not set and khojUrl
set to khoj cloud
2024-01-25 18:04:29 +05:30
Debanjum Singh Solanky
1c52ddf792 Bump up server side content indexing interval to ~1 day
Reduce server side indexing load and API request failures
2024-01-25 13:33:34 +05:30
sabaimran
0fba1e27c5 Add hint to input text for using slash commands 2024-01-25 11:56:56 +05:30
sabaimran
da6cd5ddc4
Improve subqueries for online search and prompt generation for image (#626)
* Improve subqueries for online search and prompt generation for image
- Include conversation history so that subqueries or intermediate prompts are generated with the appropriate context
2024-01-24 17:42:59 +05:30
sabaimran
dbdca7d8d1 Disable swagger UI docs in production 2024-01-24 15:23:39 +05:30
sabaimran
ddf6fd9c09 Remove valid number alert 2024-01-23 17:57:27 +05:30
Debanjum Singh Solanky
17107a0337 Release Khoj version 1.4.0 2024-01-23 10:18:31 +05:30
sabaimran
679db51453
Add support for phone number authentication with Khoj (part 2) (#621)
* Allow users to configure phone numbers with the Khoj server

* Integration of API endpoint for updating phone number

* Add phone number association and OTP via Twilio for users connecting to WhatsApp

- When verified, store the result as such in the KhojUser object

* Add a Whatsapp.svg for configuring phone number

* Change setup hint depending on whether the user has a number already connected or not

* Add an integrity check for the intl tel js dependency

* Customize the UI based on whether the user has verified their phone number

- Update API routes to make nomenclature for phone addition and verification more straightforward (just /config/phone, etc).
- If user has not verified, prompt them for another verification code (if verification is enabled) in the configuration page

* Use the verified filter only if the user is linked to an account with an email

* Add some basic documentation for using the WhatsApp client with Khoj

* Point help text to the docs, rather than landing page info

* Update messages on various callbacks and add link to docs page to learn more about the integration
2024-01-22 18:14:58 -08:00
sabaimran
58bf917775
Update the font used across Khoj desktop and web to be Tajawal (#622) 2024-01-20 23:13:33 +05:30
Debanjum
679f0f24a4
Improve Chat Input Pane Actions. Move to 1 Click Audio Chat on Mobile (#624)
## Major
### Move to single click audio chat UX on Obsidian, Desktop, Web clients
  New default UX has 1 long-press on mobile, 2-click on desktop to send transcribed audio message
  - New Audio Chat Flow
    1. Record audio while microphone button pressed
    2. Show auto-send 3s countdown timer UI for audio chat message
        Provide a visual cue around send button for how long before audio
        message is automatically sent to Khoj for response
    3. Auto-send msg in 3s unless stop send message button clicked
  - Why
    - Removes the previous default of 3 clicks required to send audio message
       The record > stop > send process to send audio messages was unclear and effortful
    - Still allows stopping message from being sent, to make correction to transcribed audio
    - Removes inadvertent long audio transcriptions if forget to press stop while recording

### Improve chat input pane actions & icons on Obsidian. Desktop, Web clients
- Use SVG icons in chat footer on web, desktop app
- Move delete icon to left of chat input. This makes it harder to inadvertently click it
- Add send button to chat input pane
- Color chat message send button to make it primary CTA
- Make chat footer shorter. Use no or round border on action buttons

## Minor
- Stop rendering empty starter questions element when no questions present
- Add round border, hover color to starter questions in web, desktop apps
- Fix auto resizing chat input box when transcribed text added
- Convert chat input into a text area in the Obsidian client
2024-01-20 21:52:56 +05:30
Debanjum Singh Solanky
ec3b837d00 Send audio message in 2-clicks on desktop to avoid holding down mic button 2024-01-20 21:40:38 +05:30
Debanjum Singh Solanky
f0daa45ae0 Move to single click audio chat UX on Obsidian client
- Capabillity
  New default UX has 1 long-press to send transcribed audio message

  - Removes the previous default of 3 clicks required to send audio message
    - The record > stop > send process to send audio messages was unclear
  - Still allows stopping message from being sent, if users want to make
    correction to transcribed audio
  - Removes inadvertent long audio transcriptions if user forgets to
    press stop when recording

- Changes
  - Record audio while microphone button pressed
  - Show auto-send 3s countdown timer UI for audio chat message
    Provide a visual cue around send button for how long before audio
    message is automatically sent to Khoj for response
  - Auto-send msg in 3s unless stop send message button clicked
2024-01-20 16:07:12 +05:30
Debanjum Singh Solanky
29a581d2b0 Move to single click audio chat UX on desktop app
- Capabillity
  New default UX has 1 long-press to send transcribed audio message

  - Removes the previous default of 3 clicks required to send audio message
    - The record > stop > send process to send audio messages was unclear
  - Still allows stopping message from being sent, if users want to make
    correction to transcribed audio
  - Removes inadvertent long audio transcriptions if user forgets to
    press stop when recording

- Changes
  - Record audio while microphone button pressed
  - Show auto-send 3s countdown timer UI for audio chat message
    Provide a visual cue around send button for how long before audio
    message is automatically sent to Khoj for response
  - Auto-send msg in 3s unless stop send message button clicked
2024-01-20 16:03:51 +05:30
Debanjum Singh Solanky
699e9ff878 Move to single click audio chat UX on web app
- Capabillity
  New default UX has 1 long-press to send transcribed audio message

  - Removes the previous default of 3 clicks required to send audio message
    - The record > stop > send process to send audio messages was unclear
  - Still allows stopping message from being sent, if users want to make
    correction to transcribed audio
  - Removes inadvertent long audio transcriptions if user forgets to
    press stop when recording

- Changes
  - Record audio while microphone button pressed
  - Show auto-send 3s countdown timer UI for audio chat message
    Provide a visual cue around send button for how long before audio
    message is automatically sent to Khoj for response
  - Auto-send msg in 3s unless stop send message button clicked
2024-01-20 15:56:46 +05:30
Debanjum Singh Solanky
26bd3533d8 Stop rendering empty starter questions element when no questions present 2024-01-20 11:39:58 +05:30
Debanjum Singh Solanky
7c8c475c3a Add round border, hover color to starter questions in web, desktop apps 2024-01-20 00:51:11 +05:30
Debanjum Singh Solanky
8a488b9e39 Fix auto resizing chat input box when transcribed text added 2024-01-20 00:48:56 +05:30
Debanjum Singh Solanky
07ca137bdf Convert chat input into a text area in the Obsidian client
This allows for better readability of multi-line messages by users.
The chat input is a text area in the other clients as well.
2024-01-20 00:48:56 +05:30
Debanjum Singh Solanky
d4552117f6 Add and improve chat input pane, actions, icons on Obsidian client
- Move delete icon to left of chat input. This makes it harder to
  inadvertently click
- Add send button to chat footer. Enter being the only way to send
  messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
2024-01-20 00:48:56 +05:30
Debanjum Singh Solanky
c0ad64d9a3 Add and improve chat input pane, actions, icons on desktop client
- Use SVG icons in chat footer on web
- Move delete icon to left of chat input. This makes it harder to
  inadvertently click
- Add send button to chat footer. Enter being the only way to send
  messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
2024-01-20 00:29:49 +05:30
Debanjum Singh Solanky
ea85ebdacb Add and improve chat input pane, actions, icons on web client
- Use SVG icons in chat footer on web
- Move delete icon to left of chat input. This makes it harder to
  inadvertently click
- Add send button to chat footer. Enter being the only way to send
  messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
2024-01-19 20:40:42 +05:30
sabaimran
039ed78253
Add support for a first-party client app to call into Khoj (Part 1) (#601)
* Add support for a first party client app
- Based on a client id and client secret, allow a first party app to call into the Khoj backend with a phone number identifier
- Add migration to add phone numbers to the KhojUser object
* Add plus in front of country code when registering a phone number.
- Decrease free tier limit to 5 (from 10)
- Return a response object when handling stripe webhooks
* Fix telemetry method which references authenticated user's client app
* Add better error handling for null phone numbers, simplify logic of authenticating user
* Pull the client_secret in the API call from the authorization header
* Add a migration merge to resolve phone number and other changes
2024-01-18 19:24:14 +05:30
Debanjum Singh Solanky
9dfe1bb003 Fix updating subscription when invoice paid. Revert renewal_date logic
The actual issue was that `get_or_create_user_by_email' tried to
create a subscription even if it already existed.

With updated logic:
- New subscription is only created when it doesn't already exist in
  `get_or_create_user_by_email'
- `set_user_subscription' just updates the subscription state as
  user subscription object creation is already managed by
  `get_or_create_user_by_email'. So the other conditionals are
  unnecessary
2024-01-18 16:20:18 +05:30
Debanjum Singh Solanky
9b1a66c969 Fix updating subscription renewal date when invoice paid 2024-01-18 14:46:10 +05:30
sabaimran
93d5cb128c Initialize embeddings to empty list before processing 2024-01-18 13:27:04 +05:30
Debanjum Singh Solanky
24af888c41 Release Khoj version 1.3.0 2024-01-18 11:42:13 +05:30
Debanjum
8b4dd16255
Fix markdownRenderer arg to allow chat responses in Obsidian plugin (#619)
- Issue
Users with Dataview plugin would have error as its markdown
post-processor expects the sourcePath to be a string

This prevents Khoj from responding to chat messages in the Obsidian
chat modal. Search via Obsidian still works but it throws the same
dataview plugin error

- Fix
Pass a string as sourcePath to markdownRenderer to fix failing chat response
and stop throwing dataview errors on search

Resolves #614, Resolves #606
2024-01-18 10:18:31 +05:30
Debanjum
c8dbe8ee7b
Improve server status check and message in Obsidian client (#617)
- Update health API to pass authenticated users their info
- Improve Khoj server status check in Khoj Obsidian client
- Show Khoj Obsidian commands even if no connection to server
- Show Khoj chat by default in Obsidian side pane instead of search
2024-01-18 10:17:35 +05:30
Debanjum Singh Solanky
f9420e1209 Show Khoj Obsidian commands even if no connection to server
Server connection check can be a little flaky in Obsidian. Don't gate
the commands behind it to improve usability of Khoj.

Previously the commands would get disabled when server connection
check failed, even though server was actually accessible
2024-01-18 10:09:20 +05:30
Debanjum Singh Solanky
36bf42a860 Show Khoj chat by default in Obsidian side pane instead of search 2024-01-18 10:09:20 +05:30
Debanjum Singh Solanky
aab75a6ead Improve Khoj server status check in Khoj Obsidian client
- Update server connection status on every edit of khoj url, api key in
  settings instead of only on plugin load

  The error message was stale if connection fixed after changes in
  Khoj plugin settings to URL or API key, like on plugin install

- Show better welcome message on first plugin install.
  Include API key setup instruction

- Show logged in user email on Khoj settings page
2024-01-18 10:09:20 +05:30
Debanjum Singh Solanky
1a46734485 Fix markdownRenderer arg to allow chat responses in Obsidian plugin
- Issue: Users with Dataview plugin would have error as its markdown
post-processor expects the sourcePath to be a string

This prevents Khoj from responding to chat messages in the Obsidian
chat modal. Search via Obsidian still works but it throws the same
dataview error

- Fix: Pass a string as sourcePath to markdownRenderer to fix
failing chat response

Resolves #614, Resolves #606
2024-01-18 10:02:50 +05:30
sabaimran
e9e49ea098
Allow custom inference endpoint for the crossencoder model (#616)
* Add support for custom inference endpoints for the cross encoder model
- Since there's not a good out of the box solution, I've deployed a custom model/handler via huggingface to support this use case.
* Use langchain.community for pdf, openai chat modules
* Add an explicit stipulation that the api endpoint for crossencoder inference should be for huggingface for now
2024-01-18 10:02:12 +05:30
Debanjum Singh Solanky
870af19ba4 Update health API to pass authenticated users their info
This allows Khoj clients to get email address associated with
user's API token for display in client UX

In anonymous mode, default user information is passed
2024-01-17 13:38:57 +05:30
Debanjum
4d30f7d1d9
Short-circuit API rate limiter for unauthenticated users (#607)
### Major
- Short-circuit API rate limiter for unauthenticated user
  Calls by unauthenticated users were failing at API rate limiter as it
  failed to access user info object. This is a bug.
  
  API rate limiter should short-circuit for unauthenicated users so a
  proper Forbidden response can be returned by API
  
  Add regression test to verify that unauthenticated users get 403
  response when calling the /chat API endpoint
  
### Minor
- Remove trailing slash to normalize khoj url in obsidian plugin settings
- Move used /api/config API controllers into separate module
- Delete unused /api/beta API endpoint
- Fix error message rendering in khoj.el, khoj obsidian chat
- Handle deprecation warnings for subscribe renew date, langchain, pydantic & logger.warn
2024-01-17 00:59:52 +05:30
Debanjum Singh Solanky
2752e0d607 Update jinja2 and axios min supported package versions 2024-01-16 18:45:38 +05:30